x
This commit is contained in:
+3
-3
@@ -55,12 +55,12 @@
|
|||||||
"local_path": "Qwen3.5-35B-A3B-GPTQ-Int4",
|
"local_path": "Qwen3.5-35B-A3B-GPTQ-Int4",
|
||||||
"dtype": "float16",
|
"dtype": "float16",
|
||||||
"quantization": "gptq",
|
"quantization": "gptq",
|
||||||
"ctx": "262144",
|
"ctx": "131072",
|
||||||
"trust_remote": true,
|
"trust_remote": true,
|
||||||
"valid_tp": [1, 2],
|
"valid_tp": [2],
|
||||||
"max_num_seqs": "6",
|
"max_num_seqs": "6",
|
||||||
"max_tokens": "4096",
|
"max_tokens": "4096",
|
||||||
"gpu_util": "0.95",
|
"gpu_util": "0.90",
|
||||||
"enforce_eager": false,
|
"enforce_eager": false,
|
||||||
"tool_call_parser": "qwen3_coder",
|
"tool_call_parser": "qwen3_coder",
|
||||||
"reasoning_parser": "qwen3",
|
"reasoning_parser": "qwen3",
|
||||||
|
|||||||
Reference in New Issue
Block a user