📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
active 2025-01-30 → 2026-04-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 448 days from 2025-01-30 to 2026-04-22. Pushes: 15 total, peak 4 in a day. Pull requests: 8 total, peak 2 in a day. Issues: 3 total, peak 1 in a day. Comments: 5 total, peak 2 in a day. Stars: 434 total, peak 33 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 |
|---|---|---|---|---|
| DefTruth | 26 | 15 | 8 | 2 |
| fpeanut | 2 | 0 | 0 | 1 |
| xiefan46 | 1 | 0 | 0 | 0 |
| Dingjifeng | 1 | 0 | 0 | 1 |
| github-actions[bot] | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#251github-actions[bot]2025-03-23 01:40[BUG] softmax_f32_kernel 和 softmax_f32x4_kernel 的实现可能有误
- Pull request#261DefTruth2025-03-22 15:59
- Pull request#261DefTruth2025-03-22 15:58
- Issue comment#260fpeanut2025-03-19 06:18mat-transpose实现重复
- Issue#260fpeanut2025-03-19 05:20mat-transpose实现重复
- ReleaseDefTruth2025-03-15 03:14v3.0.4
- Issue comment#258DefTruth2025-03-15 01:56关于mma中的一些句法的疑惑
- Pull request#257DefTruth2025-03-04 02:09
- Pull request#257DefTruth2025-03-04 02:03
- Issue#255xiefan462025-03-02 09:37Verify all the output values in C matrix in sgemm
- Pull request#254DefTruth2025-02-23 13:05
- Pull request#254DefTruth2025-02-23 13:05
- Pull request#253DefTruth2025-02-22 03:26
- Pull request#253DefTruth2025-02-22 03:26
- Issue#245DefTruth2025-02-06 07:28关于from torch.utils.cpp_extension import load的问题
- Issue comment#232DefTruth2025-02-02 11:40Question about the multi-pass Attention
- Issue comment#232Dingjifeng2025-02-02 11:10Question about the multi-pass Attention
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 434 stars here means stars gained during the window, not the repo's star count.