Added Hi Cache CPU Offloading test to CI - #1533
Draft
slokesha wants to merge 1 commit into
Draft
Conversation
Signed-off-by: slokesha <slokeshappa@habana.ai>
slokesha
had a problem deploying
to
pre-merge-approval
June 8, 2026 15:54 — with 
GitHub Actions
Error
GitHub Actions
Error
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds a new full end-to-end test that starts a vLLM server with the HiKV CPU offloading connector and runs an inference-perf workload designed to force shared-prefix KV eviction/reload behavior.
Changes:
- Added an
inference-perfworkload YAML for the HiKV CPU offload scenario. - Added a Python end-to-end runner that boots the server, runs the workload, and validates error-rate thresholds.
- Wired the new test into the full-tests CI launcher script.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| tests/full_tests/workloads/hi_cache_cpu_offload.yaml | New inference-perf workload configuration targeting shared-prefix/LRU eviction under concurrency. |
| tests/full_tests/hi_cache_cpu_offload.py | New orchestration script to start vLLM with OffloadingConnector, run inference-perf, and validate results. |
| tests/full_tests/ci_e2e_discoverable_tests.sh | Adds a new CI-discoverable test entry that installs and runs the new end-to-end script. |
| server: | ||
| type: vllm | ||
| model_name: Qwen/Qwen3-32B | ||
| base_url: http://localhost:8000 |
| import os | ||
| import subprocess | ||
| import sys | ||
| import tempfile |
| # Requires: pip install inference-perf | ||
| run_hi_cache_cpu_offload_test() { | ||
| echo "➡️ Testing HiKV Cache CPU offloading with OffloadingConnector (Qwen3-32B, TP=2)..." | ||
| pip install inference-perf --quiet |
| run_hi_cache_cpu_offload_test() { | ||
| echo "➡️ Testing HiKV Cache CPU offloading with OffloadingConnector (Qwen3-32B, TP=2)..." | ||
| pip install inference-perf --quiet | ||
| python -u "${VLLM_GAUDI_PREFIX}/tests/full_tests/hi_cache_cpu_offload.py" |
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.
No description provided.