xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-16 11:47:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support moe_wna16 as well

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
mgoin 2025-02-12 19:18:29 +00:00
parent b8510f1081
commit 243408b6b4
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@ -990,7 +990,7 @@ class ModelConfig:
return False return False
if self.quantization is not None and self.quantization not in [\ if self.quantization is not None and self.quantization not in [\
"fp8", "compressed-tensors", "awq_marlin"]: "fp8", "compressed-tensors", "awq_marlin", "moe_wna16"]:
logger.warning( logger.warning(
"MLA is not supported with %s quantization. " "MLA is not supported with %s quantization. "
"Disabling MLA.", self.quantization) "Disabling MLA.", self.quantization)