Opensource Ascend NPU Plugin for LMCache#1
Merged
matthewygf merged 2 commits intoLMCache:mainfrom Aug 18, 2025
Merged
Conversation
Signed-off-by: matthewygf <yyygggfff@hotmail.com> Co-authored-by: Marco Barletta <barlettamarco8@gmail.com> Co-authored-by: chloroethylene <jjysama@gmail.com>
Signed-off-by: matthewygf <yyygggfff@hotmail.com>
chloroethylene
pushed a commit
that referenced
this pull request
Jan 5, 2026
* Add build workflow check Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Update Dockerfile paths in build workflow Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Enable submodules in build workflow Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Add Pre-Commit & GitHub actions (#1) * Add Pre-commit lint & build test workflow action --------- Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Update build-and-test.yml - because the host-ip variable cannot work here yet, so temporarily pass for the bridgeip Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Add pull-requests permission to workflow Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Remove test report publishing step Removed the test report publishing step from the workflow. Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Add workflow to publish test results Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * enhance reports xml * Fix formatting in build-and-test workflow Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Fix formatting in report-test-results.yml Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> * Fix error message formatting in managed_mem.cpp Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com> --------- Signed-off-by: Matthew Yeung <yyygggfff@hotmail.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds Ascend NPU 910b series initial support to LMCache v0.3.3 :
Changes Made
related issue
related pr
Pre-requisite
NPU Driver version >= 24.1
CANN Tool-kit version >= 8.2
Installed compatible version of vllm-ascend, torch-npu
We currently support the following vLLM-ascend versions:
Build Instructions
pip install --no-build-isolation -v -e .Test Coverage
We ran the unit tests successfully for the main patched classes.
Related PR
This following PR in vllm-ascend is related to support LMCache
Roadmap
We currently only support eagermode execution. We plan to have the following features in the near future: