Add vLLM v0.18.1 source tree with KV transfer abort fix
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
20
third_party/vllm/.github/workflows/scripts/create_release.js
vendored
Normal file
20
third_party/vllm/.github/workflows/scripts/create_release.js
vendored
Normal file
@@ -0,0 +1,20 @@
|
||||
// Uses GitHub's API to create the release and wait for result.
|
||||
// We use a JS script since github CLI doesn't provide a way to wait for the release's creation and returns immediately.
|
||||
|
||||
module.exports = async (github, context, core) => {
|
||||
try {
|
||||
const response = await github.rest.repos.createRelease({
|
||||
draft: false,
|
||||
generate_release_notes: true,
|
||||
name: process.env.RELEASE_TAG,
|
||||
owner: context.repo.owner,
|
||||
prerelease: true,
|
||||
repo: context.repo.repo,
|
||||
tag_name: process.env.RELEASE_TAG,
|
||||
});
|
||||
|
||||
core.setOutput('upload_url', response.data.upload_url);
|
||||
} catch (error) {
|
||||
core.setFailed(error.message);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user