Conversation
wangx700
force-pushed
the
feat/pr413-npu-disk-patches
branch
from
September 15, 2026 02:14
af68281 to
ea7ec14
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds only the disk checkpoint serving patches required by the PR-413 NPU stack.
NPUWorker.pull_weights()for Ascend collective RPC.git apply --check --whitespace=nowarnagainst pinned vLLMe6bfe03and vLLM-Ascendfd815467from [NPU] Sync Ascend with main and consolidate NPU adaptations vllm-project/vime#413.8-card disk validation
Validated on Ascend NPUs 8-15 with Qwen3-4B, disk transport,
num_rollout=10, rollout batch size 4, two samples per prompt, and response length 256. The table excludes the final v10 update because it overlaps Ray/vLLM job teardown; it compares the initial sync and stable v1-v9 updates.E2E uses
perf/step_timeand covers rollout, training wait, training, and the update attributed to the step. Delta transfers about 0.66% of the model on average, but vLLM still reloads a reconstructed 7.49 GiB safetensors checkpoint on this NPU path.