Skip to content

๐Ÿš€ Accelerate inference and training of ๐Ÿค— Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

active 2025-03-26 โ†’ 2026-08-07 (UTC)

Partial coverage11,290 / 12,068 hourly files (94%) ยท 2 absent upstream ยท 775 failed, retryable2025-03-25 โ†’ 2026-08-10 (UTC)โ€” sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.3K
Pushes
227
Pull requests
127
Issues
132
Stars
270
Forks
52

Activity over time

Daily event counts in the loaded window

Line chart, 500 days from 2025-03-26 to 2026-08-07. Pushes: 227 total, peak 16 in a day. Pull requests: 127 total, peak 4 in a day. Issues: 132 total, peak 5 in a day. Comments: 358 total, peak 13 in a day. Stars: 270 total, peak 5 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 โ€” โˆ’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 โ€” stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Pull request#2475BortnikMaxim2026-08-07 16:44
  • Issue comment#351BortnikMaxim2026-08-07 16:42
    Add all available ONNX models to ORTConfigManager
  • Issue#2425github-actions[bot]2026-07-15 02:18
    Add ONNX export support for Qwen3.5/3.6 MoE (qwen3_5_moe) architecture
  • Issue comment#2436naomili09242026-06-08 06:57
    [Bug] Gemma-4 ONNX Export fails due to Mixed Head Dimensions (RoPE corruption) and MemoryError during validation for Qualcomm NPU via ONNX-Runtime
  • Issue comment#2434naomili09242026-06-08 00:58
    I follow the Documentation and I still can't fully export an ASR model to ONNX :(
  • Issue comment#2428Anai-Guo2026-06-07 01:24
    fix(cli): resolve subpackage register paths before deduplication
  • Issue#2431github-actions[bot]2026-06-03 02:24
    ONNX export support for SmolVLM2 architecture (smolvlm2)
  • Issue comment#2444HuggingFaceDocBuilderDev2026-06-02 22:51
    Bump actions/checkout from 6 to 6.0.2 in the actions group
  • Pull request#2444dependabot[bot]2026-06-02 22:48
  • Pull request#2444dependabot[bot]2026-06-02 22:48
  • Pull request#2444dependabot[bot]2026-06-02 22:48
  • Issue comment#2424Anai-Guo2026-05-28 13:15
    fix(exporters/tasks): support local timm model paths in ONNX export
  • Issue comment#2409github-actions[bot]2026-05-27 02:25
    Fix Python 3.14+ compatibility for NORMALIZED_CONFIG_CLASS
  • Issue#2412github-actions[bot]2026-05-16 02:22
    the task text-classification support in the ONNX export for gemma3_text.
  • Issue comment#2412github-actions[bot]2026-05-16 02:22
    the task text-classification support in the ONNX export for gemma3_text.
  • Issue#2436carrycooldude2026-05-11 09:05
    [Bug] Gemma-4 ONNX Export fails due to Mixed Head Dimensions (RoPE corruption) and MemoryError during validation for Qualcomm NPU via ONNX-Runtime
  • Issue#2434i-just-wanna-do-things2026-05-05 22:12
    I follow the Documentation and I still can't fully export an ASR model to ONNX :(
  • Issue comment#2397github-actions[bot]2026-04-25 02:20
    Upgrade GitHub Actions for Node 24 compatibility
  • Issue#2423antonkharkhonov2026-04-17 13:09
    Can't convert local timm models
  • Issue comment#2420Qubitium2026-04-15 12:06
    Fix gptqmodel backend check
  • Issue comment#2420jiqing-feng2026-04-14 07:43
    Fix gptqmodel backend check
  • Issue comment#2376levlbars2026-04-12 23:14
    Support qwen2_5_vl for ONNX export
  • Issue#2412github-actions[bot]2026-04-11 02:19
    the task text-classification support in the ONNX export for gemma3_text.
  • Issue comment#2412github-actions[bot]2026-04-11 02:19
    the task text-classification support in the ONNX export for gemma3_text.
  • Issue#2376github-actions[bot]2026-03-25 02:19
    Support qwen2_5_vl for ONNX export

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals โ€” 270 stars here means stars gained during the window, not the repo's star count.