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

[Hardware][CPU] Update intel_extension_for_pytorch 2.7.0 and move to requirements/cpu.txt (#18542)

Browse Source 
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
This commit is contained in:
Kay Yan 2025-05-23 19:38:42 +08:00 committed by GitHub
parent 6526e05111
commit 7ab056c273
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docker/Dockerfile.cpu
View File

@ -51,9 +51,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --upgrade pip && \ uv pip install --upgrade pip && \
uv pip install -r requirements/cpu.txt uv pip install -r requirements/cpu.txt
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install intel-openmp==2024.2.1 intel_extension_for_pytorch==2.6.0
ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so:$LD_PRELOAD" ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so:$LD_PRELOAD"
RUN echo 'ulimit -c 0' >> ~/.bashrc RUN echo 'ulimit -c 0' >> ~/.bashrc

4
requirements/cpu.txt
View File

@ -20,3 +20,7 @@ datasets # for benchmark scripts
# cpu cannot use triton 3.3.0 # cpu cannot use triton 3.3.0
triton==3.2.0; platform_machine == "x86_64" triton==3.2.0; platform_machine == "x86_64"
# Intel Extension for PyTorch, only for x86_64 CPUs
intel-openmp; platform_machine == "x86_64"
intel_extension_for_pytorch==2.7.0; platform_machine == "x86_64"

2
vllm/model_executor/layers/quantization/ipex_quant.py
View File

@ -14,7 +14,7 @@ from vllm.model_executor.layers.quantization.base_config import (
from vllm.model_executor.layers.quantization.gptq import GPTQLinearMethod from vllm.model_executor.layers.quantization.gptq import GPTQLinearMethod
from vllm.platforms import current_platform from vllm.platforms import current_platform
MIN_IPEX_VERSION = "2.5.0" MIN_IPEX_VERSION = "2.7.0"
class IPEXConfig(QuantizationConfig): class IPEXConfig(QuantizationConfig):