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 12, 02:15 UTC
Fix error while downloading dependencies for CPU backend (#29797)
Signed-off-by: Jianwei Mao <maojianwei2016@126.com>
Jianwei Mao committed
Dec 4, 2025 at 14:04 UTC
80f8af4b2fadf85403290a38c8ae77f01b6b5378
2 files changed
-2
requirements/cpu-build.txt
-1
@@ -3,7 +3,6 @@ ninja
3
packaging>=24.2
4
setuptools>=77.0.3,<81.0.0
5
setuptools-scm>=8
6
---extra-index-url https://download.pytorch.org/whl/cpu
6
torch==2.9.1+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
7
torch==2.9.1; platform_system == "Darwin" or platform_machine == "ppc64le" or platform_machine == "aarch64"
8
scons; platform_machine == "aarch64" # needed to build Arm Compute Library (ACL)
requirements/cpu.txt
-1
@@ -4,7 +4,6 @@
4
numba == 0.61.2; platform_machine != "s390x" # Required for N-gram speculative decoding
5
6
# Dependencies for CPUs
7
---extra-index-url https://download.pytorch.org/whl/cpu
7
torch==2.9.1+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
8
torch==2.9.1; platform_system == "Darwin" or platform_machine == "ppc64le" or platform_machine == "aarch64"
9