73f55bd6da
### What this PR does / why we need it?. add memcache and memfabric into dockerfile ### Does this PR introduce _any_ user-facing change? no --------- Signed-off-by: zouyida2052 <zouyida2002@gmail.com> Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
45 lines
765 B
Plaintext
45 lines
765 B
Plaintext
# Should be mirrored in pyporject.toml
|
|
cmake>=3.26
|
|
decorator
|
|
einops
|
|
numpy<2.0.0
|
|
packaging
|
|
pip
|
|
pybind11
|
|
pyyaml
|
|
regex
|
|
scipy
|
|
pandas
|
|
psutil
|
|
setuptools>=64
|
|
setuptools-scm>=8
|
|
torch==2.9.0
|
|
torchvision==0.24.0
|
|
torchaudio==2.9.0
|
|
wheel
|
|
xgrammar>=0.1.30
|
|
pandas-stubs
|
|
opencv-python-headless<=4.11.0.86 # Required to avoid numpy version conflict with vllm
|
|
compressed_tensors>=0.11.0
|
|
|
|
# Required for disaggregated prefill
|
|
msgpack
|
|
quart
|
|
|
|
# Required for N-gram speculative decoding
|
|
numba
|
|
|
|
# Required for kvpool supports memcache backend
|
|
memfabric_hybrid==1.0.8
|
|
memcache_hybrid==1.0.4
|
|
|
|
# Install torch_npu
|
|
#--pre
|
|
#--extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi
|
|
torch-npu==2.9.0
|
|
|
|
arctic-inference==0.1.1
|
|
transformers>=4.57.4
|
|
fastapi<0.124.0
|
|
triton-ascend==3.2.0
|