Skip to content

Ship correct and fast LLM kernels to PyTorch

active 2025-08-162026-03-22 (UTC)

Partial coverage11,628 / 12,802 hourly files (91%) · 2 absent upstream · 1,170 failed, retryable2025-02-232026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
858
Pushes
193
Pull requests
77
Issues
32
Stars
64
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 219 days from 2025-08-16 to 2026-03-22. Pushes: 193 total, peak 14 in a day. Pull requests: 77 total, peak 8 in a day. Issues: 32 total, peak 6 in a day. Comments: 249 total, peak 27 in a day. Stars: 64 total, peak 7 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
PaliC252543391
msaroufim225631464
jiannanWang170571854
ParamThakkar123290421
Copilot13007
shaahins11702
Laurawly10602
meta-cla[bot]8053
wychi7004
S1ro13200
karthickai3111
ZainRizvi2200
manuelcandales2110
oraluben1010

Recent activity

Latest issues, pull requests and releases

  • Pull request#205jiannanWang2026-01-14 23:52
  • Issue comment#198jiannanWang2025-12-18 16:04
    CUDA kernel registration supports
  • Pull request#203jiannanWang2025-12-17 05:09
  • Issue comment#204msaroufim2025-12-16 22:55
    Add Power-aware Benchmarking Support
  • Pull request#203meta-cla[bot]2025-12-15 21:47
  • Pull request#202meta-cla[bot]2025-12-10 19:39
  • Issue#31jiannanWang2025-11-11 18:42
    More DSLs
  • Issue comment#200karthickai2025-11-11 18:17
    [BackendBench] Add Helion DSL kernel generation support
  • Issue comment#200jiannanWang2025-11-10 23:31
    [BackendBench] Add Helion DSL kernel generation support
  • Pull request#200meta-cla[bot]2025-11-10 04:09
  • Pull request#200karthickai2025-11-10 04:09
  • Issue comment#198jiannanWang2025-10-30 20:44
    CUDA kernel registration supports
  • Pull request#194ParamThakkar1232025-10-17 03:45
  • Pull request#194meta-cla[bot]2025-10-17 03:45
  • Issue comment#185meta-cla[bot]2025-10-17 00:27
    [Model Suite] Add model correctness testing
  • Issue comment#186meta-cla[bot]2025-10-17 00:27
    [WIP] [ModelSuite] Add Performace Testing
  • Issue comment#146meta-cla[bot]2025-10-17 00:26
    [WIP] add model sources to torchbench test set
  • Issue comment#192jiannanWang2025-10-16 23:02
    Add Op Overload Directory Naming Format in DirectoryBackend
  • Issue comment#193msaroufim2025-10-16 21:46
    Added PrivateUse1 backend registration
  • Pull request#193msaroufim2025-10-16 21:46
  • Issue comment#164PaliC2025-10-16 21:39
    Added Error Logging
  • Issue comment#89ParamThakkar1232025-10-16 03:43
    Explore other backend registration mechanisms
  • Issue comment#192PaliC2025-10-16 00:15
    Add Op Overload Directory Naming Format in DirectoryBackend
  • Pull request#192meta-cla[bot]2025-10-15 18:48
  • Issue comment#183jiannanWang2025-10-03 17:40
    [ModelSuite] Add Toy Models

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 64 stars here means stars gained during the window, not the repo's star count.