Skip to content

lightweight, standalone C++ inference engine for Google's Gemma models. Google의 Gemma 모델을 위한 가볍고 독립적인 C++ 추론 엔진입니다.

C++ · active 2024-11-242026-08-09 (UTC)

Partial coverage12,907 / 15,006 hourly files (86%) · 2 absent upstream · 2,093 failed, retryable2024-11-232026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.8K
Pushes
659
Pull requests
210
Issues
27
Stars
447
Forks
69

Activity over time

Daily event counts in the loaded window

Line chart, 624 days from 2024-11-24 to 2026-08-09. Pushes: 659 total, peak 14 in a day. Pull requests: 210 total, peak 7 in a day. Issues: 27 total, peak 2 in a day. Comments: 107 total, peak 7 in a day. Stars: 447 total, peak 12 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

Recent activity

Latest issues, pull requests and releases

  • Pull request#949copybara-service[bot]2026-07-09 15:08
  • Issue comment#936google-cla[bot]2026-06-15 23:44
    Clear unconsumed args after help message to avoid aborting message
  • Issue comment#918jan-wassenberg2026-05-27 12:46
    Add Gemma 3 LM-only model variants (fixes #888)
  • Issue comment#915google-cla[bot]2026-05-13 21:58
    To support bazel the latest 9.1.0
  • Issue comment#911filmil2026-05-09 23:21
    Give a known-good example for https://github.com/google/gemma.cpp/blob/main/API_SERVER_README.md
  • Issue#911filmil2026-05-09 23:17
    Give a known-good example for https://github.com/google/gemma.cpp/blob/main/API_SERVER_README.md
  • Issue#906JesesePU2026-05-08 04:46
    TSU Protocol × Google — Open RISC-V NPU Sponsorship Proposal
  • Issue#898QuantumSorcerer022026-04-19 07:30
    Cpu and environmental errors
  • Pull request#891copybara-service[bot]2026-04-07 11:32
  • Pull request#893copybara-service[bot]2026-04-07 07:25
  • Pull request#890texasich2026-04-05 23:42
  • Pull request#886copybara-service[bot]2026-04-02 11:19
  • Pull request#872copybara-service[bot]2026-03-30 13:45
  • Issue comment#875jan-wassenberg2026-03-26 14:30
    Showcase / question: a board-proven offline language runtime on ESP32-C3, and whether this points to a more extreme form of language/runtime co-design
  • Issue comment#875Alpha-Guardian2026-03-20 11:39
    Showcase / question: a board-proven offline language runtime on ESP32-C3, and whether this points to a more extreme form of language/runtime co-design
  • Issue comment#868google-cla[bot]2026-03-11 19:29
    Internal Change
  • Issue comment#865jan-wassenberg2026-03-11 11:14
    Upgrade GitHub Actions for Node 24 compatibility
  • Pull request#859copybara-service[bot]2026-03-05 19:21
  • Pull request#858copybara-service[bot]2026-03-05 18:40
  • Issue comment#855google-cla[bot]2026-03-05 10:29
    Automated Code Change
  • Pull request#854copybara-service[bot]2026-03-04 08:27
  • Issue comment#851google-cla[bot]2026-03-02 12:14
    Rewrote flash attention to use BF16, transpose k and v, rewrote the task distribution, increase parallelism on decode, and use double the registers for the core of flash attention.
  • Pull request#849copybara-service[bot]2026-02-27 14:56
  • Pull request#844copybara-service[bot]2026-02-27 09:31
  • Pull request#846copybara-service[bot]2026-02-26 14:56

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 447 stars here means stars gained during the window, not the repo's star count.