A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 19:30 UTC
[Hardware][Intel CPU] Update torch 2.4.0 for CPU backend (#6931)
Jie Fu (傅杰) committed
Aug 2, 2024 at 23:55 UTC
c16eaac5001d9e2bfb51c9812ec0c2b9e32b8d25
2 files changed
+2
-2
Dockerfile.cpu
+1
-1
@@ -26,7 +26,7 @@ COPY ./ /workspace/vllm
26
27
WORKDIR /workspace/vllm
28
29
-RUN pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/test/cpu
29
+RUN pip install -v -r requirements-cpu.txt --extra-index-url https://download.pytorch.org/whl/cpu
30
31
# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
32
ARG VLLM_CPU_DISABLE_AVX512
requirements-cpu.txt
+1
-1
@@ -2,5 +2,5 @@
2
-r requirements-common.txt
3
4
# Dependencies for x86_64 CPUs
5
-torch == 2.4.0; platform_machine != "ppc64le"
5
+torch == 2.4.0+cpu; platform_machine != "ppc64le"
6
torchvision; platform_machine != "ppc64le" # required for the image processor of phi3v, this must be updated alongside torch