FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
active 2025-01-22 → 2026-07-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 526 days from 2025-01-22 to 2026-07-01. Pushes: 0 total, peak 0 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 2 total, peak 1 in a day. Comments: 2 total, peak 1 in a day. Stars: 169 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 — −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 |
|---|---|---|---|---|
| DrXuQian | 1 | 0 | 0 | 1 |
| nostaljic | 1 | 0 | 1 | 0 |
| charyang-ai | 1 | 0 | 0 | 0 |
| huoshenlaile | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#40huoshenlaile2025-12-18 17:01Issue with running kernel on blackwell GPUs (RTX 5090)
- Issue#43charyang-ai2025-10-29 09:45Any plan on AMD ROCm platform support?
- Issue comment#40DrXuQian2025-08-29 04:09Issue with running kernel on blackwell GPUs (RTX 5090)
- Issue#42Zephyreeze2025-07-24 09:56Potential Async Data Race in cp_async4_stream Usage - Request for Validation
- Pull request#39nostaljic2025-01-31 04:56
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 169 stars here means stars gained during the window, not the repo's star count.