x
This commit is contained in:
+4
-2
@@ -38,12 +38,13 @@
|
||||
"tool_call_parser": "qwen3_coder",
|
||||
"reasoning_parser": "qwen3",
|
||||
"enable_auto_tool_choice": true,
|
||||
"language_model_only": true,
|
||||
"served_model_name": "Qwen3.6-35B-A3B-FP8",
|
||||
"hf_model_id": "Qwen/Qwen3.6-35B-A3B-FP8"
|
||||
},
|
||||
"Qwen3.6-27B": {
|
||||
"local_path": "Qwen3.6-27B",
|
||||
"ctx": "262144",
|
||||
"ctx": "131072",
|
||||
"max_tokens": "32768",
|
||||
"max_num_batched_tokens": 16384,
|
||||
"trust_remote": true,
|
||||
@@ -53,12 +54,13 @@
|
||||
2
|
||||
],
|
||||
"max_num_seqs": 32,
|
||||
"gpu_util": "0.90",
|
||||
"gpu_util": "0.92",
|
||||
"kv_cache_dtype": "fp8",
|
||||
"enable_prefix_caching": true,
|
||||
"tool_call_parser": "qwen3_coder",
|
||||
"reasoning_parser": "qwen3",
|
||||
"enable_auto_tool_choice": true,
|
||||
"language_model_only": true,
|
||||
"served_model_name": "Qwen3.6-27B",
|
||||
"hf_model_id": "Qwen/Qwen3.6-27B"
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user