chore(frontend): bump vllm rust crates to d3e2888c - #961
Merged
Merged
Conversation
Keep the EngineCore impersonation compiling after six weeks of upstream handshake, output, and Config field growth. Co-authored-by: Cursor <cursoragent@cursor.com> Signed-off-by: susun <751080330@qq.com>
Drop the session notes from the crate-rev change. Co-authored-by: Cursor <cursoragent@cursor.com> Signed-off-by: susun <751080330@qq.com>
Signed-off-by: susun <751080330@qq.com> Co-authored-by: Cursor <cursoragent@cursor.com> Signed-off-by: susun <751080330@qq.com>
xiaguan
force-pushed
the
chore/bump-vllm-crates
branch
from
August 25, 2026 03:53
ef4c233 to
459407d
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
cc706b05(2026-07-16) tod3e2888c(vllmmainas of 2026-08-25).ec_transfer_params).pegainfer-simA/B at 128-in / 64-out / 3200 prompts / c=320: 0-fail both sides; steady-state req/s 402 vs 401; TPOT p50 still the 12.11ms sim floor.Dependency Update
vllm-chatcc706b05d3e2888cvllm-engine-core-clientcc706b05d3e2888cvllm-servercc706b05d3e2888cvllm-textcc706b05d3e2888cvllm-tokenizercc706b05d3e2888cNotable upstream: Kimi K3 rust frontend + tool/reasoning fixes, GLM-5.2 chat-template parity, MiniJinja 2.24,
protoc→protox,--max-model-lenengine-owned, per-request spec-decode metrics.Test plan
cargo test --release --locked -p pegainfer-frontend --lib— 65 passedcargo test --release --locked -p pegainfer-sim --lib— 6 passedcargo test --release --locked -p pegainfer-sim --test frontend_e2e— 13 passedvllm-benchA/B vscc706b05binary, same flags as above — 3200/0 both; steady-state throughput flat