xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 13:06:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix warning msg on quantization (#1715)

Browse Source
This commit is contained in:
Woosuk Kwon 2023-11-18 21:49:55 -08:00 committed by GitHub
parent e1054247ba
commit be66d9b125
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/config.py
View File

@ -137,9 +137,9 @@ class ModelConfig:
raise ValueError(
f"Unknown quantization method: {self.quantization}. Must "
f"be one of {supported_quantization}.")
logger.warning(f"{self.quantization} quantization is not fully "
"optimized yet. The speed can be slower than "
"non-quantized models.")
logger.warning(f"{self.quantization} quantization is not fully "
"optimized yet. The speed can be slower than "
"non-quantized models.")
def verify_with_parallel_config(
self,