x
This commit is contained in:
+8
-2
@@ -20,7 +20,7 @@
|
||||
"revision": "",
|
||||
"models": {
|
||||
"default": "Qwen3.5-35B-A3B-GPTQ-Int4",
|
||||
"selected": "Qwen3.6-35B-A3B-FP8",
|
||||
"selected": "Qwen3.6-27B-FP8",
|
||||
"profiles": {
|
||||
"Qwen3.6-35B-A3B-FP8": {
|
||||
"local_path": "Qwen3.6-35B-A3B-FP8",
|
||||
@@ -87,7 +87,13 @@
|
||||
"enable_auto_tool_choice": true,
|
||||
"language_model_only": true,
|
||||
"served_model_name": "Qwen3.6-27B-FP8",
|
||||
"hf_model_id": "Qwen/Qwen3.6-27B-FP8"
|
||||
"hf_model_id": "Qwen/Qwen3.6-27B-FP8",
|
||||
"speculative": {
|
||||
"method": "dflash",
|
||||
"model": "Qwen3.6-27B-DFlash",
|
||||
"num_speculative_tokens": 8,
|
||||
"draft_tensor_parallel_size": 1
|
||||
}
|
||||
},
|
||||
"Qwen3.5-35B-A3B-FP8": {
|
||||
"local_path": "Qwen3.5-35B-A3B-FP8",
|
||||
|
||||
Reference in New Issue
Block a user