squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CI][BugFix] Flip is_quant_method_supported condition (#5577)

Browse Source
This commit is contained in:
Michael Goin 2024-06-16 10:07:34 -04:00 committed by GitHub
parent f31c1f90e3
commit 4a6769053a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/utils.py
View File

@ -10,5 +10,5 @@ def is_quant_method_supported(quant_method: str) -> bool:
capability = torch.cuda.get_device_capability()
capability = capability[0] * 10 + capability[1]
return (capability <
return (capability >=
QUANTIZATION_METHODS[quant_method].get_min_capability())