Close-to-metal programming for AMD NPUs
active 2025-10-31 → 2026-08-03 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 277 days from 2025-10-31 to 2026-08-03. Pushes: 275 total, peak 30 in a day. Pull requests: 33 total, peak 4 in a day. Issues: 14 total, peak 2 in a day. Comments: 222 total, peak 18 in a day. Stars: 37 total, peak 8 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 |
|---|---|---|---|---|
| github-actions[bot] | 263 | 108 | 5 | 150 |
| andrej | 156 | 84 | 14 | 32 |
| hunhoffe | 76 | 47 | 3 | 14 |
| jgmelber | 33 | 27 | 1 | 0 |
| kurtis-b-1 | 30 | 5 | 6 | 10 |
| Victor-Jung | 9 | 3 | 0 | 3 |
| ypapadop-amd | 7 | 1 | 0 | 3 |
| atassis | 3 | 0 | 1 | 1 |
| alxchk | 3 | 0 | 0 | 2 |
| AngryLoki | 3 | 0 | 0 | 2 |
| hamesjan | 2 | 0 | 0 | 2 |
| Copilot | 2 | 0 | 0 | 0 |
| abhay-lal | 2 | 0 | 1 | 0 |
| astrelsky | 2 | 0 | 0 | 1 |
| IllusiveAldebaran | 1 | 0 | 0 | 0 |
| amd-wiz-3a79465917[bot] | 1 | 0 | 0 | 0 |
| maifeeulasad | 1 | 0 | 0 | 1 |
| Davidqian123 | 1 | 0 | 0 | 0 |
| pvasireddy-amd | 1 | 0 | 0 | 0 |
| tonyjie | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#142atassis2026-07-25 13:56
- Issue comment#136astrelsky2026-07-23 21:49Windows support
- Pull request#108andrej2026-04-24 21:27
- Pull request#108andrej2026-04-23 23:24
- Pull request#107x4v13r642026-04-14 18:37
- Issue#103nickbaxter182026-04-12 13:37ERT_CMD_STATE_ERROR on Strix Halo with firmware 1.1.2.65
- Issue comment#101github-actions[bot]2026-04-10 17:12Add GEMV INT 4
- Issue comment#88github-actions[bot]2026-04-06 13:39Simplifying Refactor Part 2
- Issue comment#88github-actions[bot]2026-04-03 21:06Simplifying Refactor Part 2
- Pull request#89andrej2026-04-02 21:43
- Issue comment#88github-actions[bot]2026-04-02 21:21Simplifying Refactor Part 2
- Issue comment#89github-actions[bot]2026-04-02 18:24Re-enable Phoenix support
- Issue comment#89github-actions[bot]2026-04-02 18:05Re-enable Phoenix support
- Issue comment#88github-actions[bot]2026-03-31 18:37Refactor Part 2: Integration of mlir-aie Features
- Issue comment#88github-actions[bot]2026-03-27 23:51Refactor Part 2: Integration of mlir-aie Features
- Issue comment#88github-actions[bot]2026-03-27 23:36Refactor Part 2: Integration of mlir-aie Features
- Issue comment#89github-actions[bot]2026-03-27 23:27Re-enable Phoenix support
- Issue comment#88github-actions[bot]2026-03-26 01:40Refactor Part 2: Integration of mlir-aie Features
- Issue comment#88github-actions[bot]2026-03-25 21:47Refactor Part 2
- Issue comment#87github-actions[bot]2026-03-24 22:34fix FLOP/s throughput metric in CI
- Issue comment#81github-actions[bot]2026-03-21 13:17Feature/model converter analysis
- Issue comment#76github-actions[bot]2026-03-20 22:11Reimplement llama with fused MLIR operators + simplify operators
- Issue#83tonyjie2026-03-20 20:16GEMM partition_N > 1 produces incorrect results (affects Llama final vocab projection)
- Issue comment#81github-actions[bot]2026-03-19 05:14Feature/model converter analysis
- Issue comment#81github-actions[bot]2026-03-18 02:35Feature/model converter analysis
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 37 stars here means stars gained during the window, not the repo's star count.