CUDA Templates for Linear Algebra Subroutines
active 2025-04-23 → 2025-07-17 (UTC)
Partial coverage13,585 / 16,222 hourly files (84%) · 2 absent upstream · 2,631 failed, retryable2024-10-04 → 2026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
830
Pushes
49
Pull requests
105
Issues
16
Stars
9
Forks
6
Activity over time
Daily event counts in the loaded window
Line chart, 89 days from 2025-04-23 to 2025-07-23. Pushes: 49 total, peak 5 in a day. Pull requests: 105 total, peak 6 in a day. Issues: 16 total, peak 4 in a day. Comments: 353 total, peak 32 in a day. Stars: 9 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| aacostadiaz | 196 | 44 | 58 | 45 |
| t4c1 | 132 | 0 | 5 | 75 |
| sanchitintel | 126 | 0 | 3 | 71 |
| mehdi-goli | 76 | 2 | 3 | 32 |
| joeatodd | 61 | 0 | 2 | 31 |
| taozha2 | 41 | 0 | 8 | 19 |
| muhammad-tanvir-1211 | 39 | 1 | 10 | 12 |
| jiyang1011 | 30 | 0 | 3 | 16 |
| cfgfung | 22 | 0 | 1 | 13 |
| rolandschulz | 20 | 0 | 2 | 8 |
| min-jean-cho | 13 | 0 | 2 | 8 |
| leslie-fang-intel | 10 | 0 | 0 | 7 |
| yuankuns | 9 | 0 | 0 | 4 |
| carlewis | 7 | 2 | 0 | 4 |
| pengzhao-intel | 5 | 0 | 0 | 3 |
| FMarno | 5 | 0 | 1 | 2 |
| Ruyk | 3 | 0 | 1 | 1 |
| tdeng5 | 2 | 0 | 1 | 0 |
| sunjiweiswift | 1 | 0 | 1 | 0 |
| alanzhai219 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#468rolandschulz2025-07-23 22:59[BUG] Compile fail in `09_bmg_grouped_gemm_f8`
- Issue#468rolandschulz2025-07-23 22:59[BUG] Compile fail in `09_bmg_grouped_gemm_f8`
- Pull request#470taozha22025-07-23 04:44
- Issue comment#469taozha22025-07-21 06:37Enable float fp8 scaling
- Pull request#467taozha22025-07-21 01:18
- Pull request#469taozha22025-07-21 01:09
- Pull request#467taozha22025-07-17 05:26
- Pull request#466sanchitintel2025-07-17 05:08
- Issue comment#456sanchitintel2025-07-17 04:31[FEA] Support of FP32 scales in FP8 scaledMM
- Issue#456sanchitintel2025-07-17 04:31[FEA] Support of FP32 scales in FP8 scaledMM
- Issue comment#465jiyang10112025-07-17 01:14F16xS8 S8 MMA engine
- Pull request#306jiyang10112025-07-15 07:59
- Pull request#381taozha22025-07-15 07:58
- Issue comment#461jiyang10112025-07-15 01:54avoid to allocate buffer_C if not necessary
- Pull request#463taozha22025-07-15 01:39
- Pull request#463taozha22025-07-15 01:39
- Pull request#436t4c12025-07-14 10:22
- Issue comment#436t4c12025-07-14 10:22Unify f8 and mixed input pipelines
- Pull request#459aacostadiaz2025-07-14 09:22
- Issue comment#460taozha22025-07-14 07:19enable int8_t mma for mixed dtype
- Pull request#454aacostadiaz2025-07-10 12:04
- Pull request#458aacostadiaz2025-07-10 12:04
- Issue comment#462aacostadiaz2025-07-10 09:26[BUG] Cannot compile BMG Flash Attention when ElementOutput is bfloat_16t
- Issue comment#458jiyang10112025-07-10 08:45header files inclusion
- Issue comment#460taozha22025-07-10 05:06enable int8_t mma for mixed dtype
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 9 stars here means stars gained during the window, not the repo's star count.