Enable optimized-baseline benchmark on Intel XPU#1512
Open
WenjiaoYue wants to merge 2 commits into
Open
Conversation
Add an Intel XPU (gpu.intel.com/xe, classic device plugin) variant of the optimized-baseline guide so the scenario runs on Intel GPUs. - config/scenarios/guides/optimized-baseline-xpu.yaml: XPU scenario (accelerator intel-xe, device=xpu, --enforce-eager, RWO storage for kind, podSecurityContext supplementalGroups for /dev/dri access, Qwen3-0.6B). - config/specification/guides/optimized-baseline-xpu.yaml.j2: spec pointing at the XPU scenario (mirrors optimized-baseline.yaml.j2). - config/templates/jinja/13_ms-values.yaml.j2: indent the first line of decode/prefill podSecurityContext so supplementalGroups renders as valid nested YAML (previously the first key landed at column 0). Required by the XPU scenario; no-op for scenarios that do not set podSecurityContext. Signed-off-by: WenjiaoYue <wenjiao.yue@intel.com>
WenjiaoYue
requested review from
Vezio,
achandrasekar,
kalantar,
maugustosilva,
mengmeiye and
namasl
as code owners
Contributor
|
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. |
Contributor
There was a problem hiding this comment.
Pull request overview
Enables running the “optimized-baseline” benchmark variant on Intel XPU by introducing a dedicated XPU scenario/spec and adjusting the modelservice values template so podSecurityContext renders as valid nested YAML when provided.
Changes:
- Add an Intel XPU scenario (
optimized-baseline-xpu) targetinggpu.intel.com/xe, using an XPU vLLM image and XPU-specificvllm serveflags (including--enforce-eager). - Add a corresponding specification file that points to the new XPU scenario.
- Fix Jinja indentation for
decode/prefill.podSecurityContextso the first rendered key is correctly indented underpodSecurityContext:.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| config/templates/jinja/13_ms-values.yaml.j2 | Fixes YAML rendering for podSecurityContext by indenting the first line of the dumped YAML. |
| config/specification/guides/optimized-baseline-xpu.yaml.j2 | Adds a spec entry that selects the XPU optimized-baseline scenario. |
| config/scenarios/guides/optimized-baseline-xpu.yaml | Introduces the Intel XPU scenario (accelerator, image, command, storage, and security context). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| size: 50Gi | ||
| maxModelLen: 16000 | ||
| blockSize: 16 | ||
| gpuMemoryUtilization: 0.9 |
55 tasks
Introduce a shared config/templates/values/overlays/xpu.yaml carrying the machine-related deltas (accelerator, images, decode/prefill acceleratorType) so every XPU guide can reuse it instead of duplicating per-guide YAML. Add a values_overlays mechanism to the renderer (render_plans.py + cli.py) that deep-merges overlays declared under values_file.overlays onto defaults, before the guide scenario and CLI overrides. Slim optimized-baseline-xpu scenario to keep only guide-specific bits and wire the overlay in via the specification's values_file.overlays. Signed-off-by: WenjiaoYue <wenjiao.yue@intel.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.
Enable optimized-baseline benchmark on Intel XPU.