Pre-built wheels for llama-cpp-python across platforms and CUDA versions
active 2025-11-03 → 2026-05-30 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 209 days from 2025-11-03 to 2026-05-30. Pushes: 3 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 3 total, peak 1 in a day. Comments: 5 total, peak 2 in a day. Stars: 22 total, peak 2 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
- Issue comment#4PATATAJEC2026-04-20 21:22not support AVX 512
- Issue comment#3dougeeai2026-04-18 21:08Python 3.12 Cuda 12.1 sm86 win wheel is built against cuda 13
- Releasedougeeai2026-04-18 21:00v0.3.20 — Ampere (sm_86), CUDA 12.1, Python 3.10–3.13
- Issue#9dougeeai2026-04-18 19:51Rtx Pro 6000 Blackwell SM 120
- Issue comment#9dougeeai2026-04-18 19:51Rtx Pro 6000 Blackwell SM 120
- Releasedougeeai2026-04-18 19:39v0.3.20 — Ampere (sm_86), CUDA 13.0, Python 3.10–3.13
- Releasedougeeai2026-04-18 19:38v0.3.20 — Turing (sm_75), CUDA 13.0, Python 3.10–3.13
- Issue comment#8Winnougan2026-03-29 09:03llama_cpp_python-0.3.16+cuda13.0.sm86.ampere-cp313-cp313-win_amd64.whl -- for 30XX GPU -- results in a 404 file not found
- Issue#73m1rc1kk2026-01-18 16:42Linux support about
- Issue#4ai802334072025-12-15 21:25not support AVX 512
- Issue comment#2amberfay2025-11-20 02:25404 whl
- Releasedougeeai2025-11-09 20:35llama-cpp-python 0.3.16 + CUDA 13.0 sm75 Turing - Python 3.12 - Windows x64
- Releasedougeeai2025-11-09 20:28llama-cpp-python 0.3.16 + CUDA 11.8 sm75 Turing - Python 3.11 - Windows x64
- Releasedougeeai2025-11-09 20:24llama-cpp-python 0.3.16 + CUDA 13.0 sm100 Blackwell - Python 3.13 - Windows x64
- Releasedougeeai2025-11-03 04:02llama-cpp-python 0.3.16 + CUDA 11.8 sm89 Ada Lovelace - Python 3.10 - Windows x64
- Releasedougeeai2025-11-03 04:01llama-cpp-python 0.3.16 + CUDA 11.8 sm89 Ada Lovelace - Python 3.11 - Windows x64
- Releasedougeeai2025-11-03 04:01llama-cpp-python 0.3.16 + CUDA 11.8 sm89 Ada Lovelace - Python 3.12 - Windows x64
- Releasedougeeai2025-11-03 03:59llama-cpp-python 0.3.16 + CUDA 12.1 sm89 Ada Lovelace - Python 3.10 - Windows x64
- Releasedougeeai2025-11-03 03:56llama-cpp-python 0.3.16 + CUDA 12.1 sm89 Ada Lovelace - Python 3.12 - Windows x64
- Releasedougeeai2025-11-03 03:55llama-cpp-python 0.3.16 + CUDA 12.1 sm89 Ada Lovelace - Python 3.13 - Windows x64
- Releasedougeeai2025-11-03 03:54llama-cpp-python 0.3.16 + CUDA 13.0 sm89 Ada Lovelace - Python 3.10 - Windows x64
- Releasedougeeai2025-11-03 03:51llama-cpp-python 0.3.16 + CUDA 13.0 sm89 Ada Lovelace - Python 3.11 - Windows x64
- Releasedougeeai2025-11-03 03:44llama-cpp-python 0.3.16 + CUDA 11.8 sm86 Ampere - Python 3.10 - Windows x64
- Releasedougeeai2025-11-03 03:42llama-cpp-python 0.3.16 + CUDA 11.8 sm86 Ampere - Python 3.13 - Windows x64
- Releasedougeeai2025-11-03 03:39llama-cpp-python 0.3.16 + CUDA 12.1 sm86 Ampere - Python 3.11 - Windows x64
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 22 stars here means stars gained during the window, not the repo's star count.