Skip to content

High-level, optionally asynchronous Rust bindings to llama.cpp | fork

active 2023-12-272026-05-20 (UTC)

Complete coverage26,789 / 26,789 hourly files (100%) · 2 absent upstream2023-08-152026-09-04 (UTC)
Events
675
Pushes
121
Pull requests
98
Issues
52
Stars
225
Forks
42

Activity over time

Daily event counts in the loaded window

Line chart, 876 days from 2023-12-27 to 2026-05-20. Pushes: 121 total, peak 11 in a day. Pull requests: 98 total, peak 14 in a day. Issues: 52 total, peak 5 in a day. Comments: 74 total, peak 7 in a day. Stars: 225 total, peak 10 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#99adelmorad273-cmyk2026-04-21 00:36
  • Issue#98TheOneWhoWill2025-08-12 05:04
    Qwen 3 and Qwen 2vl Support on llama
  • Issue comment#97werruww2025-05-07 01:38
    run?
  • Issue comment#96werruww2025-05-07 00:43
    Colab
  • Issue comment#96werruww2025-05-06 22:02
    Colab
  • Issue comment#96werruww2025-05-04 21:01
    Colab
  • Issue#96werruww2025-05-04 03:28
    Colab
  • Issue comment#86ilovethensa2025-02-04 19:08
    How to see logs from across FFI boundary?
  • Issue#95FireFragment2024-12-08 18:39
    Linking error with `whisper-rs` when using vulkan: multiple definitions of symbol
  • Pull request#94smoelius2024-11-10 15:03
  • Issue comment#90paulstansifer2024-09-26 20:33
    Building with latest version of llama.cpp
  • Issue comment#76richard-62024-07-08 08:49
    getting called `Result::unwrap()` on an `Err` value: DecodeFailed(1) while building chat example.
  • Issue comment#77MatthewCash2024-06-24 23:30
    n_tokens_all <= cparams.n_batch
  • Issue comment#93FlorianDevPhynix2024-06-14 14:24
    set_context and advance_context with same text, generate different completion output
  • Issue#93FlorianDevPhynix2024-06-14 14:14
    set_context and advance_context with same text, generate different completion output
  • Issue#92cooperll2024-06-03 17:43
    Issues with Gemma 2b v1.1, all quants.
  • Issue comment#90cooperll2024-06-03 17:37
    Building with latest version of llama.cpp
  • Issue comment#90vargad2024-05-29 21:10
    Building with latest version of llama.cpp
  • Pull request#91vargad2024-05-29 20:23
  • Issue#90cooperll2024-05-27 23:41
    Building with latest version of llama.cpp
  • Issue comment#87Arisa-Snowbell2024-05-25 03:44
    CUDA is really slow compared to kobold.cpp I compiled from AUR, same backend
  • Issue#89jeberger2024-05-14 06:26
    Add support for building with mingw
  • Pull request#88zh2172024-05-08 14:24
  • Issue#87Arisa-Snowbell2024-05-08 09:45
    CUDA is really slow compared to kobold.cpp I compiled from AUR, same backend
  • Issue comment#77pedro-devv2024-05-07 18:11
    n_tokens_all <= cparams.n_batch

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 225 stars here means stars gained during the window, not the repo's star count.