Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
23 lines
976 B
Plaintext
23 lines
976 B
Plaintext
# Common dependencies
|
|
-r common.txt
|
|
|
|
setuptools==77.0.3 # this version can reuse CMake build dir
|
|
|
|
numba == 0.61.2; platform_machine != "s390x" # Required for N-gram speculative decoding
|
|
|
|
# Dependencies for CPUs
|
|
torch==2.10.0+cpu; platform_machine == "x86_64" or platform_machine == "s390x"
|
|
torch==2.10.0; platform_machine == "aarch64" or platform_system == "Darwin" or platform_machine == "ppc64le" or platform_machine == "riscv64"
|
|
|
|
# required for the image processor of minicpm-o-2_6, this must be updated alongside torch
|
|
torchaudio; platform_machine != "s390x" and platform_machine != "riscv64"
|
|
|
|
# required for the image processor of phi3v, this must be updated alongside torch
|
|
torchvision; platform_machine != "s390x" and platform_machine != "riscv64"
|
|
|
|
# Intel Extension for PyTorch, only for x86_64 CPUs
|
|
intel-openmp==2024.2.1; platform_machine == "x86_64"
|
|
|
|
# Use this to gather CPU info and optimize based on ARM Neoverse cores
|
|
py-cpuinfo; platform_machine == "aarch64"
|