xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-10 00:57:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix MoE BNB version (#22260)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-08-06 10:56:22 +08:00 committed by GitHub
parent 6a51530437
commit 8e6c7e873f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -412,12 +412,12 @@ class BitsAndBytesMoEMethod(FusedMoEMethodBase):
def __init__(self, quant_config: BitsAndBytesConfig): def __init__(self, quant_config: BitsAndBytesConfig):
try: try:
import bitsandbytes import bitsandbytes
if bitsandbytes.__version__ < "0.45.3": if bitsandbytes.__version__ < "0.46.1":
raise ImportError("bitsandbytes version is wrong. Please " raise ImportError("bitsandbytes version is wrong. Please "
"install bitsandbytes>=0.45.3.") "install bitsandbytes>=0.46.1.")
except ImportError as err: except ImportError as err:
raise ImportError("Please install bitsandbytes>=0.45.3 via " raise ImportError("Please install bitsandbytes>=0.46.1 via "
"`pip install bitsandbytes>=0.45.3` to use " "`pip install bitsandbytes>=0.46.1` to use "
"bitsandbytes quantizer.") from err "bitsandbytes quantizer.") from err
self.topk_indices_dtype = None self.topk_indices_dtype = None
self.quant_config = quant_config self.quant_config = quant_config