Skip to content

feat(connectors): add williamhtan/kernelsight - #831

Closed
m7m2od wants to merge 1 commit into
OpenTSLM:mainfrom
m7m2od:feature/kernelsight-connector
Closed

m7m2od wants to merge 1 commit into
OpenTSLM:mainfrom
m7m2od:feature/kernelsight-connector

Conversation

@m7m2od

@m7m2od m7m2od commented Nov 20, 2026

Copy link
Copy Markdown

Summary

Adds a connector for the KernelSight GPU-trace dataset (williamhtan/kernelsight). Each profiled run becomes one Record: a 24-channel by 512-bin counter trace with its workload labels.

Changes

  • connector.py, dataset.yaml and requirements.txt under datasets/williamhtan/kernelsight
  • Connector tests in tests/test_connector.py

Testing

  • pytest on the connector: 8 passed
  • ruff check and ruff format --check clean
  • Rebased on current main

Part of the TimeNet Online Hackathon: onboard a dataset, then fine-tune a time-series language model on it.

🤖 Generated with Claude Code

KernelSight: 1,444 H100 GPU counter snapshots (24 channels x 512 bins)
with per-segment L1/L2 workload labels, from the pinned Hub release.

- One Record per snapshot, 24 Signals in five channel-group Sources,
  a per-snapshot RegularAxis from the bin edges.
- Segment L1/L2 interval annotations, plus multi-hot-only overlap runs
  (track=multihot) for the 472 cutlass_ws_overlap snapshots.
- One ClassificationTask per snapshot on the authors' dominant_l1.
- Split grouped by problem (KernelBench dtype/seed variants stay
  together), stratified by class, 3/1/1, seed 42; the released split
  memberships are kept in record metadata.
- Reads only numeric npz arrays (allow_pickle=False).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@m7m2od
m7m2od marked this pull request as draft November 20, 2026 12:57
@m7m2od m7m2od closed this Nov 20, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant