docker: rebase vllm.patch onto vLLM 0.24.0 (drop sleep hunk, add abort+usage)#308
Open
aoshen02 wants to merge 1 commit into
Open
docker: rebase vllm.patch onto vLLM 0.24.0 (drop sleep hunk, add abort+usage)#308aoshen02 wants to merge 1 commit into
aoshen02 wants to merge 1 commit into
Conversation
…t+usage) The base image moved to vllm/vllm-openai:latest-ubuntu2404 (v0.24.0). - Drop the vllm/v1/engine/core.py partial-wake/dummy-batch hunk: the `if not self.model_executor.is_sleeping` guard is now upstream in 0.24.0, so patching it is unnecessary (and would fail to apply). - Keep all2all_utils.py (max_num_tokens) hunk. - Add the /abort_requests endpoint (api_router.py, vllm-project#296) and the GenerateResponse.usage field (disagg/protocol.py, vllm-project#303). All three hunks verified with `git apply --check` against a real vllm/vllm-openai:v0.24.0-ubuntu2404 container (RC=0; minor line offsets absorbed by git apply's context matching). Signed-off-by: aoshen02 <aoshen@inferact.ai> Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Documentation build overview
31 files changed ·
|
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Base image moved to
vllm/vllm-openai:latest-ubuntu2404(v0.24.0). Rebasedocker/patch/latest/vllm.patchaccordingly:vllm/v1/engine/core.pypartial-wake / dummy-batch hunk — theif not self.model_executor.is_sleepingguard is now upstream in 0.24.0, so patching it is unnecessary and would fail to apply.all2all_utils.py(max_num_tokens = moe.max_num_tokens) hunk./abort_requestsendpoint (api_router.py, from fix(rollout): abort vLLM rollout via delete-type /abort_requests #296) andGenerateResponse.usagefield (disagg/protocol.py, from [Bugfix][Rollout] Wire prefix_cache_hit_rate through vLLM usage #303).Verification
All three hunks checked with
git apply --check --allow-emptyagainst a realvllm/vllm-openai:v0.24.0-ubuntu2404container → RC=0 (minor line offsets absorbed by git apply's context matching).