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

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>

docker/Dockerfile

@@ -498,7 +498,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
         uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
     else \
-        uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.3' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
+        uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.46.1' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
     fi
 
 ENV VLLM_USAGE_SOURCE production-docker-image

docs/features/quantization/bnb.md

@@ -10,7 +10,7 @@ Compared to other quantization methods, BitsAndBytes eliminates the need for cal
 Below are the steps to utilize BitsAndBytes with vLLM.
 
 ```bash
-pip install bitsandbytes>=0.45.3
+pip install bitsandbytes>=0.46.1
 ```
 
 vLLM reads the model's config file and supports both in-flight quantization and pre-quantized checkpoint.

requirements/nightly_torch_test.txt

@@ -34,7 +34,7 @@ tokenizers==0.21.1
 huggingface-hub[hf_xet]>=0.30.0  # Required for Xet downloads.
 schemathesis>=3.39.15 # Required for openai schema test.
 # quantization
-bitsandbytes>=0.45.3
+bitsandbytes>=0.46.1
 buildkite-test-collector==0.1.9
 
 

requirements/test.in

@@ -39,7 +39,7 @@ tokenizers==0.21.1
 huggingface-hub[hf_xet]>=0.33.0  # Required for Xet downloads.
 schemathesis>=3.39.15 # Required for openai schema test.
 # quantization
-bitsandbytes>=0.45.3
+bitsandbytes==0.46.1
 buildkite-test-collector==0.1.9
 
 

requirements/test.txt

@@ -45,7 +45,7 @@ backoff==2.2.1
     # via
     #   -r requirements/test.in
     #   schemathesis
-bitsandbytes==0.45.3
+bitsandbytes==0.46.1
     # via -r requirements/test.in
 black==24.10.0
     # via datamodel-code-generator

vllm/config.py

@@ -969,7 +969,7 @@ class ModelConfig:
 
     def _verify_bnb_config(self) -> None:
         """
-        The current version of bitsandbytes (0.45.3) with 8-bit models does not
+        The current version of bitsandbytes (0.46.1) with 8-bit models does not
         yet support CUDA graph.
         # TODO Remove this when bitsandbytes supports.
         """

vllm/model_executor/layers/quantization/bitsandbytes.py

@@ -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

vllm/model_executor/model_loader/bitsandbytes_loader.py

@@ -183,12 +183,12 @@ class BitsAndBytesModelLoader(BaseModelLoader):
         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
 
         hf_weights_files, use_safetensors = self._prepare_weights(