amd-r9700-vllm-toolboxes/benchmarks/benchmark_results_nvidia-ada5000/openai_gpt-oss-20b_tp1_server.log

WARNING 12-10 19:34:31 [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=3207) INFO 12-10 19:34:31 [api_server.py:1772] vLLM API server version 0.12.0
(APIServer pid=3207) INFO 12-10 19:34:31 [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': 32768, 'gpu_memory_utilization': 0.95, 'max_num_seqs': 64}
(APIServer pid=3207) The argument `trust_remote_code` is to be used with Auto classes. It has no effect here and is ignored.
(APIServer pid=3207) INFO 12-10 19:34:38 [model.py:637] Resolved architecture: GptOssForCausalLM
Parse safetensors files: 100%|██████████| 3/3 [00:00<00:00, 15.19it/s]
(APIServer pid=3207) INFO 12-10 19:34:38 [model.py:1750] Using max model len 32768
(APIServer pid=3207) INFO 12-10 19:34:38 [scheduler.py:228] Chunked prefill is enabled with max_num_batched_tokens=2048.
(APIServer pid=3207) INFO 12-10 19:34:38 [config.py:274] Overriding max cuda graph capture size to 1024 for performance.
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:48 [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=32768, 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=3315) INFO 12-10 19:34:48 [parallel_state.py:1200] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.17.0.3:45235 backend=nccl
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:48 [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=3315) INFO 12-10 19:34:49 [gpu_model_runner.py:3467] Starting to load model openai/gpt-oss-20b...
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:49 [cuda.py:411] Using TRITON_ATTN attention backend out of potential backends: ['TRITON_ATTN']
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:49 [layer.py:379] Enabled separate cuda stream for MoE shared_experts
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:49 [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<00:00, 3.18it/s]
Loading safetensors checkpoint shards: 67% Completed | 2/3 [00:00<00:00, 2.54it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:01<00:00, 2.35it/s]
Loading safetensors checkpoint shards: 100% Completed | 3/3 [00:01<00:00, 2.45it/s]
(EngineCore_DP0 pid=3315)
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:51 [default_loader.py:308] Loading weights took 1.33 seconds
(EngineCore_DP0 pid=3315) WARNING 12-10 19:34:51 [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=3315) INFO 12-10 19:34:52 [gpu_model_runner.py:3549] Model loading took 13.7194 GiB memory and 2.859378 seconds
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:54 [backends.py:655] Using cache directory: /root/.cache/vllm/torch_compile_cache/e445850299/rank_0_0/backbone for vLLM's torch.compile
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:54 [backends.py:715] Dynamo bytecode transform time: 2.11 s
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:55 [backends.py:257] Cache the graph for dynamic shape for later use
(EngineCore_DP0 pid=3315) INFO 12-10 19:34:59 [backends.py:288] Compiling a graph for dynamic shape takes 4.24 s
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:05 [monitor.py:34] torch.compile takes 6.35 s in total
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:06 [gpu_worker.py:359] Available KV cache memory: 15.51 GiB
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:06 [kv_cache_utils.py:1286] GPU KV cache size: 338,832 tokens
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:06 [kv_cache_utils.py:1291] Maximum concurrency for 32,768 tokens per request: 19.38x
Capturing CUDA graphs (mixed prefill-decode, PIECEWISE): 100%|██████████| 83/83 [00:03<00:00, 26.19it/s]
Capturing CUDA graphs (decode, FULL): 100%|██████████| 11/11 [00:02<00:00, 4.07it/s]
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:13 [gpu_model_runner.py:4466] Graph capturing finished in 6 secs, took 0.75 GiB
(EngineCore_DP0 pid=3315) INFO 12-10 19:35:13 [core.py:254] init engine (profile, create kv cache, warmup model) took 20.84 seconds
(APIServer pid=3207) INFO 12-10 19:35:14 [api_server.py:1520] Supported tasks: ['generate']
(APIServer pid=3207) WARNING 12-10 19:35:15 [serving_responses.py:215] For gpt-oss, we ignore --enable-auto-tool-choice and always enable tool use.
(APIServer pid=3207) INFO 12-10 19:35:17 [api_server.py:1847] Starting vLLM API server 0 on http://127.0.0.1:8000
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:38] Available routes are:
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /openapi.json, Methods: GET, HEAD
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /docs, Methods: GET, HEAD
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /docs/oauth2-redirect, Methods: GET, HEAD
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /redoc, Methods: GET, HEAD
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /health, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /load, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /pause, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /resume, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /is_paused, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /tokenize, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /detokenize, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/models, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /version, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/responses, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/responses/{response_id}, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/responses/{response_id}/cancel, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/messages, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/chat/completions, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/completions, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/audio/transcriptions, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/audio/translations, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /scale_elastic_ep, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /is_scaling_elastic_ep, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /inference/v1/generate, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /ping, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /ping, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /invocations, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /metrics, Methods: GET
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /classify, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/embeddings, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /score, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/score, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /rerank, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v1/rerank, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /v2/rerank, Methods: POST
(APIServer pid=3207) INFO 12-10 19:35:17 [launcher.py:46] Route: /pooling, Methods: POST
(APIServer pid=3207) INFO: Started server process [3207]
(APIServer pid=3207) INFO: Waiting for application startup.
(APIServer pid=3207) INFO: Application startup complete.
(APIServer pid=3207) INFO: 127.0.0.1:42050 - "GET /v1/models HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38400 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38416 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:35:38 [loggers.py:236] Engine 000: Avg prompt throughput: 41.0 tokens/s, Avg generation throughput: 63.7 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38416 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38416 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:35:48 [loggers.py:236] Engine 000: Avg prompt throughput: 173.7 tokens/s, Avg generation throughput: 205.0 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.2%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:45124 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38416 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:35:58 [loggers.py:236] Engine 000: Avg prompt throughput: 210.1 tokens/s, Avg generation throughput: 189.2 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:08 [loggers.py:236] Engine 000: Avg prompt throughput: 211.3 tokens/s, Avg generation throughput: 154.8 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34314 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34314 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:18 [loggers.py:236] Engine 000: Avg prompt throughput: 225.3 tokens/s, Avg generation throughput: 197.2 tokens/s, Running: 4 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34314 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34314 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34314 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:28 [loggers.py:236] Engine 000: Avg prompt throughput: 370.0 tokens/s, Avg generation throughput: 224.2 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.4%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36658 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36666 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37488 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37494 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37500 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37500 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:38 [loggers.py:236] Engine 000: Avg prompt throughput: 389.0 tokens/s, Avg generation throughput: 215.4 tokens/s, Running: 6 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.6%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38430 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37500 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:48 [loggers.py:236] Engine 000: Avg prompt throughput: 212.4 tokens/s, Avg generation throughput: 161.9 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39306 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39312 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39306 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39318 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39312 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:36:58 [loggers.py:236] Engine 000: Avg prompt throughput: 291.9 tokens/s, Avg generation throughput: 287.3 tokens/s, Running: 7 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:39306 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39306 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39318 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:38420 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39312 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:08 [loggers.py:236] Engine 000: Avg prompt throughput: 401.8 tokens/s, Avg generation throughput: 376.1 tokens/s, Running: 8 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:39326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39306 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:18 [loggers.py:236] Engine 000: Avg prompt throughput: 156.9 tokens/s, Avg generation throughput: 188.8 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:28 [loggers.py:236] Engine 000: Avg prompt throughput: 33.5 tokens/s, Avg generation throughput: 216.0 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34330 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:38 [loggers.py:236] Engine 000: Avg prompt throughput: 312.2 tokens/s, Avg generation throughput: 179.5 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34330 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34330 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:53224 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:53224 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:48 [loggers.py:236] Engine 000: Avg prompt throughput: 128.3 tokens/s, Avg generation throughput: 281.7 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.5%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:53224 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56096 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:56116 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39328 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:34330 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:37:58 [loggers.py:236] Engine 000: Avg prompt throughput: 154.1 tokens/s, Avg generation throughput: 201.8 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:56816 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39388 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:08 [loggers.py:236] Engine 000: Avg prompt throughput: 72.5 tokens/s, Avg generation throughput: 24.0 tokens/s, Running: 2 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:39390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39398 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39398 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36418 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36432 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36444 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39390 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36432 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:18 [loggers.py:236] Engine 000: Avg prompt throughput: 166.2 tokens/s, Avg generation throughput: 281.5 tokens/s, Running: 3 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:36418 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39388 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36444 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36432 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36444 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39388 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36432 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:60330 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:60340 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:28 [loggers.py:236] Engine 000: Avg prompt throughput: 242.7 tokens/s, Avg generation throughput: 170.7 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.3%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39388 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:36444 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:39374 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:38 [loggers.py:236] Engine 000: Avg prompt throughput: 83.9 tokens/s, Avg generation throughput: 259.6 tokens/s, Running: 1 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.1%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:48 [loggers.py:236] Engine 000: Avg prompt throughput: 1.2 tokens/s, Avg generation throughput: 23.1 tokens/s, Running: 0 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.0%, Prefix cache hit rate: 0.0%
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48214 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:38:58 [loggers.py:236] Engine 000: Avg prompt throughput: 827.3 tokens/s, Avg generation throughput: 414.1 tokens/s, Running: 19 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 16.9%
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48214 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:08 [loggers.py:236] Engine 000: Avg prompt throughput: 1215.2 tokens/s, Avg generation throughput: 787.8 tokens/s, Running: 22 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 33.2%
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48184 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48192 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:18 [loggers.py:236] Engine 000: Avg prompt throughput: 844.7 tokens/s, Avg generation throughput: 897.4 tokens/s, Running: 24 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 41.1%
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48214 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40916 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:28 [loggers.py:236] Engine 000: Avg prompt throughput: 537.5 tokens/s, Avg generation throughput: 884.2 tokens/s, Running: 15 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.1%, Prefix cache hit rate: 45.0%
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40916 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:38 [loggers.py:236] Engine 000: Avg prompt throughput: 983.3 tokens/s, Avg generation throughput: 792.5 tokens/s, Running: 34 reqs, Waiting: 0 reqs, GPU KV cache usage: 2.6%, Prefix cache hit rate: 44.9%
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:48 [loggers.py:236] Engine 000: Avg prompt throughput: 903.2 tokens/s, Avg generation throughput: 989.5 tokens/s, Running: 23 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 40.5%
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40916 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37506 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40916 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37484 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:39:58 [loggers.py:236] Engine 000: Avg prompt throughput: 678.2 tokens/s, Avg generation throughput: 779.8 tokens/s, Running: 18 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 37.7%
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:08 [loggers.py:236] Engine 000: Avg prompt throughput: 624.5 tokens/s, Avg generation throughput: 832.1 tokens/s, Running: 24 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.4%, Prefix cache hit rate: 35.5%
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52054 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48128 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:18 [loggers.py:236] Engine 000: Avg prompt throughput: 778.6 tokens/s, Avg generation throughput: 1132.5 tokens/s, Running: 27 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.9%, Prefix cache hit rate: 33.0%
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52054 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37474 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:28 [loggers.py:236] Engine 000: Avg prompt throughput: 672.1 tokens/s, Avg generation throughput: 840.3 tokens/s, Running: 19 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 31.1%
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48144 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48204 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42872 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48174 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54642 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52054 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42890 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54638 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:38 [loggers.py:236] Engine 000: Avg prompt throughput: 1219.4 tokens/s, Avg generation throughput: 759.6 tokens/s, Running: 18 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 28.8%
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:48 [loggers.py:236] Engine 000: Avg prompt throughput: 361.4 tokens/s, Avg generation throughput: 667.9 tokens/s, Running: 17 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.0%, Prefix cache hit rate: 28.1%
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:40:58 [loggers.py:236] Engine 000: Avg prompt throughput: 834.4 tokens/s, Avg generation throughput: 729.9 tokens/s, Running: 23 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.5%, Prefix cache hit rate: 26.6%
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40896 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:41:08 [loggers.py:236] Engine 000: Avg prompt throughput: 999.2 tokens/s, Avg generation throughput: 805.7 tokens/s, Running: 16 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.0%, Prefix cache hit rate: 24.8%
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:41:18 [loggers.py:236] Engine 000: Avg prompt throughput: 631.9 tokens/s, Avg generation throughput: 663.6 tokens/s, Running: 18 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.9%, Prefix cache hit rate: 23.9%
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:41:28 [loggers.py:236] Engine 000: Avg prompt throughput: 667.6 tokens/s, Avg generation throughput: 740.0 tokens/s, Running: 16 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.2%, Prefix cache hit rate: 22.9%
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:58326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:41:38 [loggers.py:236] Engine 000: Avg prompt throughput: 657.4 tokens/s, Avg generation throughput: 835.9 tokens/s, Running: 19 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.3%, Prefix cache hit rate: 22.0%
(APIServer pid=3207) INFO: 127.0.0.1:40936 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48164 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37464 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54610 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48222 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37476 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37486 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52026 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:58326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52038 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48156 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:58326 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42910 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:37492 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:54624 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48240 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48234 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48248 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:52020 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59878 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59884 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:42940 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:48210 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59846 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59888 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:40920 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59894 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59902 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59908 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59918 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59924 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO: 127.0.0.1:59884 - "POST /v1/completions HTTP/1.1" 200 OK
(APIServer pid=3207) INFO 12-10 19:41:48 [loggers.py:236] Engine 000: Avg prompt throughput: 1117.5 tokens/s, Avg generation throughput: 829.5 tokens/s, Running: 33 reqs, Waiting: 0 reqs, GPU KV cache usage: 1.8%, Prefix cache hit rate: 20.7%
(APIServer pid=3207) INFO 12-10 19:41:58 [loggers.py:236] Engine 000: Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 656.4 tokens/s, Running: 5 reqs, Waiting: 0 reqs, GPU KV cache usage: 0.7%, Prefix cache hit rate: 20.7%