EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[Misc] add memfabric and memcache into requirements(#8748)

Browse Source 
### 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>
This commit is contained in:
zouyida2052
2026-04-29 09:30:15 +08:00
committed by GitHub
parent 2e2aaa2fae
commit 73f55bd6da
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
requirements.txt
View File

@@ -22,13 +22,17 @@ pandas-stubs
opencv-python-headless<=4.11.0.86 # Required to avoid numpy version conflict with vllm opencv-python-headless<=4.11.0.86 # Required to avoid numpy version conflict with vllm
compressed_tensors>=0.11.0 compressed_tensors>=0.11.0
# requirements for disaggregated prefill # Required for disaggregated prefill
msgpack msgpack
quart quart
# Required for N-gram speculative decoding # Required for N-gram speculative decoding
numba numba
# Required for kvpool supports memcache backend
memfabric_hybrid==1.0.8
memcache_hybrid==1.0.4
# Install torch_npu # Install torch_npu
#--pre #--pre
#--extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi #--extra-index-url https://mirrors.huaweicloud.com/ascend/repos/pypi