[vLLM][moe] Keep batched moe reference activation eager, guard CUDA stream-capture checks, and update skiplist#7440
Draft
sarah12121212 wants to merge 4 commits into
Draft
[vLLM][moe] Keep batched moe reference activation eager, guard CUDA stream-capture checks, and update skiplist#7440sarah12121212 wants to merge 4 commits into
sarah12121212 wants to merge 4 commits into
Conversation
# Conflicts: # scripts/vllm/vllm-fix.patch
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 updates the vLLM patch for batched MoE XPU coverage.
The patch:
compile_native=Falsetorch.cuda.is_current_stream_capturing()behindcurrent_platform.is_cuda()tests/kernels/moe/test_batched_moe.py::test_fused_moe_batched_expertsin the default and Xe2 MoE skiplists to theWorkspaceManager not initialized errorsection.CI Validation:
PVC:
BMG: