cjw/amd-r9700-vllm-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
9acf1322e1cdb4b223af8b771af4841576a308cb
amd-r9700-vllm-toolboxes/benchmarks/benchmark_results_nvidia-a100/openai_gpt-oss-20b_tp1_server.log
T
cjw a04b9ef9c5 x
2026-03-26 20:50:00 +08:00

117 KiB
Raw Blame History

WARNING 12-10 10:51:19 [argparse_utils.py:195] With `vllm serve`, you should provide the model as a positional argument or in a config file instead of via the `--model` option. The `--model` option will be removed in v0.13.
(APIServer pid=15750) INFO 12-10 10:51:19 [api_server.py:1772] vLLM API server version 0.12.0
(APIServer pid=15750) INFO 12-10 10:51:19 [utils.py:253] non-default args: {'model_tag': 'openai/gpt-oss-20b', 'host': '127.0.0.1', 'model': 'openai/gpt-oss-20b', 'trust_remote_code': True, 'max_model_len': 24000, 'max_num_seqs': 64}
(APIServer pid=15750) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=15750) INFO 12-10 10:51:29 [model.py:637] Resolved architecture: GptOssForCausalLM
Parse safetensors files: 100%|██████████| 3/3 [00:00<00:00, 9.27it/s]
(APIServer pid=15750) INFO 12-10 10:51:30 [model.py:1750] Using max model len 24000
(APIServer pid=15750) INFO 12-10 10:51:30 [scheduler.py:228] Chunked prefill is enabled with max_num_batched_tokens=2048.
(APIServer pid=15750) INFO 12-10 10:51:30 [config.py:274] Overriding max cuda graph capture size to 1024 for performance.
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:39 [core.py:93] Initializing a V1 LLM engine (v0.12.0) with config: model='openai/gpt-oss-20b', speculative_config=None, tokenizer='openai/gpt-oss-20b', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=24000, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, disable_custom_all_reduce=False, quantization=mxfp4, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='openai_gptoss', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01), seed=0, served_model_name=openai/gpt-oss-20b, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'level': None, 'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::kda_attention', 'vllm::sparse_attn_indexer'], 'compile_mm_encoder': False, 'compile_sizes': [], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512, 528, 544, 560, 576, 592, 608, 624, 640, 656, 672, 688, 704, 720, 736, 752, 768, 784, 800, 816, 832, 848, 864, 880, 896, 912, 928, 944, 960, 976, 992, 1008, 1024], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'eliminate_noops': True, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 1024, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>}, 'local_cache_dir': None}
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:40 [parallel_state.py:1200] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.17.0.2:59277 backend=nccl
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:40 [parallel_state.py:1408] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank 0
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:41 [gpu_model_runner.py:3467] Starting to load model openai/gpt-oss-20b...
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:41 [cuda.py:411] Using TRITON_ATTN attention backend out of potential backends: ['TRITON_ATTN']
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:41 [layer.py:379] Enabled separate cuda stream for MoE shared_experts
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:41 [mxfp4.py:162] Using Marlin backend
Loading safetensors checkpoint shards: 0% Completed | 0/3 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 33% Completed | 1/3 [00:00<00:01, 1.81it/s]
Loading safetensors checkpoint shards: 67% Completed | 2/3 [00:01<00:00, 1.52it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:02<00:00, 1.45it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:02<00:00, 1.49it/s]
(EngineCore_DP0 pid=16016)
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:44 [default_loader.py:308] Loading weights took 2.14 seconds
(EngineCore_DP0 pid=16016) WARNING 12-10 10:51:44 [marlin_utils_fp4.py:226] Your GPU does not have native support for FP4 computation but FP4 quantization is being used. Weight-only FP4 compression will be used leveraging the Marlin kernel. This may degrade performance for compute-heavy workloads.
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:45 [gpu_model_runner.py:3549] Model loading took 13.7025 GiB memory and 4.053831 seconds
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:50 [backends.py:655] Using cache directory: /root/.cache/vllm/torch_compile_cache/09d46d6ca4/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:50 [backends.py:715] Dynamo bytecode transform time: 3.97 s
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:50 [backends.py:257] Cache the graph for dynamic shape for later use
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:54 [backends.py:288] Compiling a graph for dynamic shape takes 3.92 s
(EngineCore_DP0 pid=16016) INFO 12-10 10:51:58 [monitor.py:34] torch.compile takes 7.89 s in total
(EngineCore_DP0 pid=16016) INFO 12-10 10:52:00 [gpu_worker.py:359] Available KV cache memory: 21.09 GiB
(EngineCore_DP0 pid=16016) INFO 12-10 10:52:00 [kv_cache_utils.py:1286] GPU KV cache size: 460,688 tokens
(EngineCore_DP0 pid=16016) INFO 12-10 10:52:00 [kv_cache_utils.py:1291] Maximum concurrency for 24,000 tokens per request: 35.18x
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 83/83 [00:04<00:00, 16.83it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 11/11 [00:00<00:00, 17.09it/s]
(EngineCore_DP0 pid=16016) INFO 12-10 10:52:07 [gpu_model_runner.py:4466] Graph capturing finished in 7 secs, took 2.67 GiB
(EngineCore_DP0 pid=16016) INFO 12-10 10:52:07 [core.py:254] init engine (profile, create kv cache, warmup model) took 21.87 seconds
(APIServer pid=15750) INFO 12-10 10:52:11 [api_server.py:1520] Supported tasks: ['generate']
(APIServer pid=15750) WARNING 12-10 10:52:11 [serving_responses.py:215] For gpt-oss, we ignore --enable-auto-tool-choice and always enable tool use.
(APIServer pid=15750) INFO 12-10 10:52:13 [api_server.py:1847] Starting vLLM API server 0 on http://127.0.0.1:8000
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:38] Available routes are:
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /openapi.json, Methods: HEAD, GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /docs, Methods: HEAD, GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: HEAD, GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /redoc, Methods: HEAD, GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /pause, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /resume, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /is_paused, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/responses, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/messages, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/completions, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/audio/transcriptions, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/audio/translations, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /classify, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/embeddings, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /score, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/score, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /rerank, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v1/rerank, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=15750) INFO 12-10 10:52:13 [launcher.py:46] Route: /pooling, Methods: POST
(APIServer pid=15750) INFO: Started server process [15750]
(APIServer pid=15750) INFO: Waiting for application startup.
(APIServer pid=15750) INFO: Application startup complete.
(APIServer pid=15750) INFO: 127.0.0.1:38740 - "GET /v1/models HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:52:34 [loggers.py:236] Engine 000: Avg prompt throughput: 1.2 tokens/s, Avg generation throughput: 6.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42818 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42818 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:52:44 [loggers.py:236] Engine 000: Avg prompt throughput: 114.9 tokens/s, Avg generation throughput: 220.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42138 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42794 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:52:54 [loggers.py:236] Engine 000: Avg prompt throughput: 205.8 tokens/s, Avg generation throughput: 175.3 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:42784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:04 [loggers.py:236] Engine 000: Avg prompt throughput: 188.6 tokens/s, Avg generation throughput: 159.0 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:14 [loggers.py:236] Engine 000: Avg prompt throughput: 318.1 tokens/s, Avg generation throughput: 145.9 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:24 [loggers.py:236] Engine 000: Avg prompt throughput: 205.8 tokens/s, Avg generation throughput: 223.3 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:42808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41376 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:60044 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:34 [loggers.py:236] Engine 000: Avg prompt throughput: 425.6 tokens/s, Avg generation throughput: 180.4 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41378 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:44 [loggers.py:236] Engine 000: Avg prompt throughput: 247.7 tokens/s, Avg generation throughput: 260.9 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40152 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40160 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:53:54 [loggers.py:236] Engine 000: Avg prompt throughput: 336.2 tokens/s, Avg generation throughput: 217.4 tokens/s, Running: 6 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40152 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40160 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40160 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:04 [loggers.py:236] Engine 000: Avg prompt throughput: 169.5 tokens/s, Avg generation throughput: 361.9 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:53244 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40160 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:53256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:14 [loggers.py:236] Engine 000: Avg prompt throughput: 456.9 tokens/s, Avg generation throughput: 252.5 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:24 [loggers.py:236] Engine 000: Avg prompt throughput: 32.8 tokens/s, Avg generation throughput: 232.9 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40148 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:34 [loggers.py:236] Engine 000: Avg prompt throughput: 185.5 tokens/s, Avg generation throughput: 150.7 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:33504 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:33504 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:44 [loggers.py:236] Engine 000: Avg prompt throughput: 255.5 tokens/s, Avg generation throughput: 282.2 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:54:54 [loggers.py:236] Engine 000: Avg prompt throughput: 68.4 tokens/s, Avg generation throughput: 222.4 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40134 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:50614 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:40128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:04 [loggers.py:236] Engine 000: Avg prompt throughput: 103.6 tokens/s, Avg generation throughput: 65.3 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:37454 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37454 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37454 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37466 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49276 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49276 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37454 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:14 [loggers.py:236] Engine 000: Avg prompt throughput: 110.7 tokens/s, Avg generation throughput: 199.9 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:49276 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49296 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37466 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49276 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:37454 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:24 [loggers.py:236] Engine 000: Avg prompt throughput: 134.1 tokens/s, Avg generation throughput: 175.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:59258 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59272 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59272 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59258 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59272 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59286 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59272 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59294 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59258 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:49290 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59258 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59258 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:34 [loggers.py:236] Engine 000: Avg prompt throughput: 269.3 tokens/s, Avg generation throughput: 288.0 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:59272 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59286 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:44 [loggers.py:236] Engine 000: Avg prompt throughput: 46.5 tokens/s, Avg generation throughput: 69.8 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:55:54 [loggers.py:236] Engine 000: Avg prompt throughput: 41.0 tokens/s, Avg generation throughput: 41.1 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.9%
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:04 [loggers.py:236] Engine 000: Avg prompt throughput: 820.4 tokens/s, Avg generation throughput: 648.0 tokens/s, Running: 9 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 17.4%
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:14 [loggers.py:236] Engine 000: Avg prompt throughput: 1263.3 tokens/s, Avg generation throughput: 818.7 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 34.0%
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:24 [loggers.py:236] Engine 000: Avg prompt throughput: 817.9 tokens/s, Avg generation throughput: 996.2 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 41.5%
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:34 [loggers.py:236] Engine 000: Avg prompt throughput: 607.5 tokens/s, Avg generation throughput: 769.4 tokens/s, Running: 11 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 45.9%
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:44 [loggers.py:236] Engine 000: Avg prompt throughput: 876.1 tokens/s, Avg generation throughput: 955.6 tokens/s, Running: 17 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 44.8%
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:56:54 [loggers.py:236] Engine 000: Avg prompt throughput: 988.4 tokens/s, Avg generation throughput: 820.6 tokens/s, Running: 12 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 40.0%
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45796 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:04 [loggers.py:236] Engine 000: Avg prompt throughput: 591.8 tokens/s, Avg generation throughput: 801.7 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 37.6%
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:14 [loggers.py:236] Engine 000: Avg prompt throughput: 755.7 tokens/s, Avg generation throughput: 894.8 tokens/s, Running: 20 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 35.0%
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:24 [loggers.py:236] Engine 000: Avg prompt throughput: 752.7 tokens/s, Avg generation throughput: 1174.4 tokens/s, Running: 11 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 32.7%
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:34 [loggers.py:236] Engine 000: Avg prompt throughput: 769.2 tokens/s, Avg generation throughput: 719.4 tokens/s, Running: 9 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 30.6%
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41612 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55256 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45780 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:44 [loggers.py:236] Engine 000: Avg prompt throughput: 1069.9 tokens/s, Avg generation throughput: 758.1 tokens/s, Running: 6 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 28.7%
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45830 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:57:54 [loggers.py:236] Engine 000: Avg prompt throughput: 353.8 tokens/s, Avg generation throughput: 647.2 tokens/s, Running: 6 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 27.9%
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:04 [loggers.py:236] Engine 000: Avg prompt throughput: 796.9 tokens/s, Avg generation throughput: 783.2 tokens/s, Running: 13 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 26.5%
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:14 [loggers.py:236] Engine 000: Avg prompt throughput: 1046.2 tokens/s, Avg generation throughput: 806.4 tokens/s, Running: 7 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 24.7%
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:24 [loggers.py:236] Engine 000: Avg prompt throughput: 569.8 tokens/s, Avg generation throughput: 617.2 tokens/s, Running: 10 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 23.9%
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:34 [loggers.py:236] Engine 000: Avg prompt throughput: 727.4 tokens/s, Avg generation throughput: 824.8 tokens/s, Running: 8 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 22.8%
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45772 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:44 [loggers.py:236] Engine 000: Avg prompt throughput: 785.7 tokens/s, Avg generation throughput: 765.4 tokens/s, Running: 7 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 21.8%
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59472 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45750 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59480 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41620 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45742 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55250 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59490 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:59494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55574 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45766 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55232 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45770 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45790 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45798 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45806 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55264 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45784 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45820 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45770 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45806 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:41618 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45834 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45808 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:55578 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO: 127.0.0.1:45798 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=15750) INFO 12-10 10:58:54 [loggers.py:236] Engine 000: Avg prompt throughput: 920.8 tokens/s, Avg generation throughput: 1024.1 tokens/s, Running: 14 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.8%, Prefix cache hit rate: 20.7%
(APIServer pid=15750) INFO 12-10 10:58:59 [launcher.py:110] Shutting down FastAPI HTTP server.
Reference in New Issue View Git Blame Copy Permalink