Modern RL Post-training Infrastructure: Optimized for NVIDIA/AMD GPUs with a focus on vLLM integration, Triton kernels, and transparent hardware-aware scaling.
active 2026-06-06 → 2026-08-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 76 days from 2026-06-06 to 2026-08-20. Pushes: 38 total, peak 3 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 12 total, peak 5 in a day. Comments: 14 total, peak 3 in a day. Stars: 7 total, peak 3 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 |
|---|---|---|---|---|
| Flink-ddd | 26 | 13 | 1 | 1 |
| inaniloquentee | 23 | 18 | 0 | 2 |
| coderabbitai[bot] | 12 | 0 | 0 | 8 |
| KJLdefeated | 8 | 4 | 1 | 2 |
| a-kaa | 5 | 1 | 1 | 1 |
| CyberSecurityErial | 2 | 2 | 0 | 0 |
| Dnoob | 1 | 0 | 1 | 0 |
| z1ying | 1 | 0 | 0 | 0 |
| JLiu4Coding | 1 | 0 | 0 | 0 |
| hihaluemen | 1 | 0 | 0 | 0 |
| EthanZero2Hero | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#324coderabbitai[bot]2026-08-20 12:27[wip]feat(ascend): add RMSNorm Ascend C kernel
- Pull request#282Flink-ddd2026-08-07 16:56
- Issue comment#229coderabbitai[bot]2026-07-18 22:45feat(ws2): add cross-config alignment V1 CPU framework
- Issue#226a-kaa2026-07-14 17:08[WS1][CI] The GPU architecture unmatch in GPU CI.
- Issue#205Flink-ddd2026-07-04 05:44[readme][doc] Add entry to WA community chat group #192
- Pull request#204KJLdefeated2026-07-02 13:32
- Issue#191Flink-ddd2026-06-26 05:30[CI] Support dynamic multi-GPU architecture testing (sm80/86/90/100) to fix NoneType extension load failures
- Issue#114Flink-ddd2026-06-21 14:57[WS2] RNG / randomness-source alignment
- Issue#136Flink-ddd2026-06-21 14:55[WS4] Layer-wise hidden-state alignment probe
- Issue comment#164a-kaa2026-06-21 13:44test(ws1): add elementwise and RoPE invariance audit
- Pull request#162Dnoob2026-06-20 18:29
- Issue comment#94inaniloquentee2026-06-19 08:37[FEAT][executors]: implement stateless zero-KV scoring executor
- Issue#113Flink-ddd2026-06-15 02:19[WS2] Distributed chain test
- Issue#113Flink-ddd2026-06-15 02:19[WS2] Distributed chain test
- Issue#113Flink-ddd2026-06-15 02:19[WS2] Distributed chain test
- Issue#113Flink-ddd2026-06-15 02:19[WS2] Distributed chain test
- Issue#113Flink-ddd2026-06-15 02:19[WS2] Distributed chain test
- Issue comment#105inaniloquentee2026-06-13 06:23[Bugfix][ci]: enable gpu-ci for fork PRs with secure checkout
- Issue#87KJLdefeated2026-06-08 01:59[FEAT][kernels] SM90 fused-logp (TMA) kernel cannot build or run on SM120 (Blackwell); Ask support for SM120 (Blackwell)
- Pull request#85a-kaa2026-06-07 18:31
- Issue#81Flink-ddd2026-06-07 15:58[BUG] Temperature applied twice in FlashInfer sampling path
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 7 stars here means stars gained during the window, not the repo's star count.