### What this PR does / why we need it? 1. Fix rank set in DP scenario. The new poc version of torch-npu support setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the rank set in `DPEngineCoreProc` directly instead of calculating local rank across dp by hand in the patched `_init_data_parallel` Closes: https://github.com/vllm-project/vllm-ascend/issues/1170 2. Bump torch-npu version to 2.5.1.post1.dev20250528 Closes: https://github.com/vllm-project/vllm-ascend/pull/1242 Closes: https://github.com/vllm-project/vllm-ascend/issues/1232 ### How was this patch tested? CI passed with new added test. --------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Icey <1790571317@qq.com> Co-authored-by: Icey <1790571317@qq.com>
28 lines
423 B
Plaintext
28 lines
423 B
Plaintext
# Should be mirrored in pyporject.toml
|
|
cmake>=3.26
|
|
decorator
|
|
einops
|
|
numpy<2.0.0
|
|
packaging
|
|
pip
|
|
pybind11
|
|
pyyaml
|
|
scipy
|
|
setuptools>=64
|
|
setuptools-scm>=8
|
|
torch>=2.5.1
|
|
torchvision<0.21.0
|
|
wheel
|
|
|
|
# requirements for disaggregated prefill
|
|
msgpack
|
|
quart
|
|
|
|
# Required for N-gram speculative decoding
|
|
numba
|
|
|
|
# Install torch_npu
|
|
--pre
|
|
--extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi
|
|
torch-npu==2.5.1.post1.dev20250528
|