enh: update helm charts to new llm-d-async config values - #636
Draft
evacchi wants to merge 4 commits into
Draft
Conversation
evacchi
force-pushed
the
async-processor-config-migration
branch
from
August 6, 2026 15:26
8cee818 to
e7db731
Compare
|
Unsigned commits detected! Please sign your commits. For instructions on how to set up GPG/SSH signing and verify your commits, please see GitHub Documentation. |
evacchi
force-pushed
the
async-processor-config-migration
branch
from
August 6, 2026 16:06
e7db731 to
964aa4a
Compare
Signed-off-by: Edoardo Vacchi <evacchi@users.noreply.github.com>
Signed-off-by: Edoardo Vacchi <evacchi@users.noreply.github.com>
evacchi
force-pushed
the
async-processor-config-migration
branch
from
August 20, 2026 12:56
964aa4a to
dade6ec
Compare
evacchi
marked this pull request as ready for review
August 20, 2026 12:56
evacchi
requested review from
j-mok-dev,
lioraron,
vishbhat,
yizhaodev and
zdtsw
as code owners
August 20, 2026 12:56
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the repository’s e2e configs, deployment scripts, and documentation to match the newer llm-d-async configuration schema and naming (e.g., ap.transport / ap.transportConfig and llm-d-async chart/deployment identifiers), keeping batch-gateway aligned with the upstream dispatcher project.
Changes:
- Switched dispatcher Helm values from
messageQueueImpl/redis.*totransport/transportConfigacross e2e values, examples, docs, and benchmark deployment. - Updated scripts and e2e logic to look for
llm-d-asyncnaming (chart path and deployment/service identifiers). - Refreshed trace/e2e documentation strings to refer to
llm-d-asyncinstead ofasync-processor.
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| test/e2e/dispatcher/helm-values.yaml | Updates dispatcher Helm values to the new transport-based config format. |
| test/e2e/dispatcher/helm-values-scrape.yaml | Same as above for endpoint-scrape gate scenario. |
| test/e2e/dispatcher/helm-values-prometheus.yaml | Same as above for prometheus-query gate scenario. |
| test/e2e/dispatcher_test.go | Updates e2e detection/comments to match llm-d-async naming. |
| test/e2e/dispatcher_otel_test.go | Updates Jaeger query/service naming and comments for llm-d-async. |
| scripts/dev-deploy-dispatcher.sh | Updates chart reference and deployment wait targets to llm-d-async. |
| examples/deploy-demo/deploy-k8s.sh | Updates demo deploy script chart/image and values to new transport config + new deployment name. |
| docs/guides/deploy-k8s.md | Updates deployment guide snippets for new chart/image and transport config values. |
| docs/design/batch-dispatcher-queue-design.md | Updates design doc to describe the new transport-config document format. |
| benchmarks/setup.sh | Updates benchmark scenario deployment flags and wait target to match new chart/resource naming. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| "max_concurrency": "100", | ||
| "baseline": "0.05" | ||
| { | ||
| "result_queue_name": "llm-d-async:results:optimized-baseline:$batch", |
evacchi
marked this pull request as draft
August 20, 2026 13:12
Contributor
Author
|
re-drafting no upstream release yet |
Signed-off-by: Edoardo Vacchi <evacchi@users.noreply.github.com>
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.
Why is this PR needed?
llm-d-async PRs llm-d/llm-d-async#388 and llm-d/llm-d-async#378 update to a cleaner config format; even though the old format is supported, we can keep the two codebases tightly aligned and avoid deprecation warnings.
What does this PR do?
Updates the Helm charts, scripts and tests to align to the llm-d-async codebase. Since the change is not merged yet, this PR is draft, and we might wait for a formal release before merging.
How was this tested?
Checklist
git commit -s) per DCOmake ci)make test-e2e)Related Issues
llm-d/llm-d-async#388 and llm-d/llm-d-async#378