biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Quantization] Bump to use latest bitsandbytes (#20424)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2025-07-03 21:58:46 +08:00
committed by GitHub
parent 7f0367109e
commit 1819fbda63
8 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/layers/quantization/bitsandbytes.py
View File

@@ -156,12 +156,12 @@ class BitsAndBytesLinearMethod(LinearMethodBase):
def __init__(self, quant_config: BitsAndBytesConfig):
try:
import bitsandbytes
if bitsandbytes.__version__ < "0.45.3":
if bitsandbytes.__version__ < "0.46.1":
raise ImportError("bitsandbytes version is wrong. Please "
"install bitsandbytes>=0.45.3.")
"install bitsandbytes>=0.46.1.")
except ImportError as err:
raise ImportError("Please install bitsandbytes>=0.45.3 via "
"`pip install bitsandbytes>=0.45.3` to use "
raise ImportError("Please install bitsandbytes>=0.46.1 via "
"`pip install bitsandbytes>=0.46.1` to use "
"bitsandbytes quantizer.") from err
self.quant_config = quant_config