helion-rag: retrieval-augmented autotuning over CI artifacts#3045
Draft
IshanAryendu wants to merge 1 commit into
Draft
helion-rag: retrieval-augmented autotuning over CI artifacts#3045IshanAryendu wants to merge 1 commit into
IshanAryendu wants to merge 1 commit into
Conversation
meta-cla
Bot
added
the
CLA Signed
IshanAryendu
force-pushed
the
helion-rag-pr
branch
2 times, most recently
from
bf2f040 to
84d2609
Compare
Adds scripts/helion_rag: turns CI autotuning artifacts into a searchable corpus and serves tiered lookups (Tier-0 exact workload_key match -> Tier-1 FAISS similarity -> Tier-2 miss), so a known workload returns its measured-best config instead of re-autotuning. Includes the package, unit tests, pyproject, README, and setup-helion-rag.sh. Builds on the per-config perf_stats dataset from #2861.
IshanAryendu
force-pushed
the
helion-rag-pr
branch
from
84d2609 to
fa86c2c
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds
scripts/helion_rag/— retrieval-augmented autotuning for Helion. It turns CI autotuning artifacts into a searchable corpus and serves tiered lookups:workload_keymatch → returns the measured-best config directly (no autotune)Includes the
helion_ragpackage (CLI, corpus/index/lookup, ingest/upload, runtime hook, hardware/manifest resolution), unit tests,pyproject.toml,README.md, andsetup-helion-rag.sh.Stacked on #2861 — depends on the per-config
perf_statsdataset it produces.