This commit is contained in:
2026-04-23 13:50:03 +08:00
parent 99025e1c7e
commit 6fbfba3505
+22
View File
@@ -63,6 +63,28 @@
"served_model_name": "Qwen3.6-35B-A3B-FP8", "served_model_name": "Qwen3.6-35B-A3B-FP8",
"hf_model_id": "Qwen/Qwen3.6-35B-A3B-FP8" "hf_model_id": "Qwen/Qwen3.6-35B-A3B-FP8"
}, },
"Qwen3.6-27B": {
"local_path": "Qwen3.6-27B",
"dtype": "auto",
"ctx": "131072",
"trust_remote": true,
"enforce_eager": false,
"valid_tp": [
1,
2
],
"max_num_seqs": 32,
"max_tokens": "16384",
"gpu_util": "0.90",
"kv_cache_dtype": "fp8",
"enable_prefix_caching": true,
"max_num_batched_tokens": 16384,
"tool_call_parser": "qwen3_coder",
"reasoning_parser": "qwen3",
"enable_auto_tool_choice": true,
"served_model_name": "Qwen3.6-27B",
"hf_model_id": "Qwen/Qwen3.6-27B"
},
"Qwen3.5-35B-A3B-FP8": { "Qwen3.5-35B-A3B-FP8": {
"local_path": "Qwen3.5-35B-A3B-FP8", "local_path": "Qwen3.5-35B-A3B-FP8",
"dtype": "float16", "dtype": "float16",