LLM inference in C/C++
C++ · active 2026-03-09 → 2026-08-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 152 days from 2026-03-09 to 2026-08-07. Pushes: 61 total, peak 9 in a day. Pull requests: 38 total, peak 29 in a day. Issues: 5 total, peak 1 in a day. Comments: 44 total, peak 6 in a day. Stars: 30 total, peak 4 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
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| khosravipasha | 78 | 49 | 11 | 14 |
| github-actions[bot] | 24 | 0 | 24 | 0 |
| Copilot | 19 | 1 | 0 | 9 |
| bri-prism | 12 | 11 | 1 | 0 |
| pl752 | 10 | 0 | 0 | 10 |
| zcattacz | 4 | 0 | 0 | 4 |
| claudlos | 3 | 0 | 0 | 1 |
| carlosfundora | 2 | 0 | 1 | 1 |
| Slach | 1 | 0 | 0 | 0 |
| rosmur | 1 | 0 | 0 | 1 |
| soyelmismo | 1 | 0 | 0 | 1 |
| Marxist-Leninist | 1 | 0 | 0 | 1 |
| philtomson | 1 | 0 | 0 | 1 |
| Y-Cyan-Zhang | 1 | 0 | 1 | 0 |
| wildcattrio | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#71khosravipasha2026-07-20 06:54Please provide how to use the release downloads as they're not complete llama.cpp archives.
- Pull request#73bri-prism2026-07-17 00:33
- Issue comment#34khosravipasha2026-05-31 03:09Q1_0 repack kernels for Arm NEON+DP
- Issue comment#34pl7522026-05-18 08:29Q1_0 repack kernels for Arm NEON+DP
- Issue comment#33pl7522026-05-17 06:14Optimized ARM NEON q1_0 dot
- Issue comment#21khosravipasha2026-05-05 06:24(Prototype) q1_0 nrc = 2 and diabolic tiles branches
- Issue#24khosravipasha2026-04-19 00:03WebGPU backend roadmap for Q1_0 kernels?
- Issue comment#24khosravipasha2026-04-19 00:03WebGPU backend roadmap for Q1_0 kernels?
- Issue#26khosravipasha2026-04-18 00:10Bonsai Q1_0 benchmarks — Strix Halo Vulkan (gfx1151)
- Pull request#25khosravipasha2026-04-15 01:22
- Issue comment#21khosravipasha2026-04-13 23:55(Prototype) q1_0 nrc = 2 and diabolic tiles branches
- Issue#23khosravipasha2026-04-12 03:15Oh yh that was codex sorry about didn't expect to be so aggressive and thought it was confined to me own repos
- Issue comment#23khosravipasha2026-04-12 03:14Oh yh that was codex sorry about didn't expect to be so aggressive and thought it was confined to me own repos
- Issue comment#17khosravipasha2026-04-09 22:24Feature Request: Do you plan to include support for MCP?
- Issue comment#21pl7522026-04-09 10:56(Prototype) q1_0 nrc = 2 branches
- Pull request#21github-actions[bot]2026-04-09 08:21
- Issue comment#10Marxist-Leninist2026-04-08 08:43(Performance) Optimized x86 and generic q1_0(_g128) dot
- Issue comment#4khosravipasha2026-04-08 00:17fix: Q1_0_g128 CPU dot product int truncation
- Issue comment#6khosravipasha2026-04-08 00:14fix: Q1_0_g128 x86 CPU kernel - correct output + AVX2/AVX-512 VNNI
- Issue comment#10pl7522026-04-07 19:43(Performance) Optimized x86 and generic q1_0(_g128) dot
- Issue comment#10pl7522026-04-07 06:55(Performance) Optimized x86 and generic q1_0(_g128) dot
- Issue comment#9khosravipasha2026-04-07 04:27vulkan: add Q1_0_g128 (1-bit ternary) shader support
- Pull request#9khosravipasha2026-04-07 04:18
- Pull request#9khosravipasha2026-04-07 04:18
- Pull request#9khosravipasha2026-04-07 04:18
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 30 stars here means stars gained during the window, not the repo's star count.