Skip to content

Pull requests: RL-Align/RL-Kernel

New pull request New
45 Open 181 Closed
45 Open 181 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

perf(rocm): MFMA batch-invariant GEMM and chunked Triton attention for strict R/R platform: rocm Specific tasks specific to AMD graphics cards (such as CK, bpreshuffle/FA)
#396 opened Sep 9, 2026 by Flink-ddd Collaborator • Draft
1
feat(musa): add native deterministic gemm kernel MUSA
#395 opened Sep 9, 2026 by Arlo-mt Loading…
4
fix(rocm): stabilize direct paged CK attention for bitwise R/R platform: rocm Specific tasks specific to AMD graphics cards (such as CK, bpreshuffle/FA)
#394 opened Sep 9, 2026 by inaniloquentee Collaborator Loading…
1
Musa support native fused logp kernel MUSA
#392 opened Sep 8, 2026 by Arlo-mt Loading…
8
[P5-2] Add deterministic clamp_swiglu_weighted CUDA kernel deepseek-P5 DSv4 platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations)
#389 opened Sep 6, 2026 by hsiuyee Loading…
12
[DSv4][P5-5] Shared Expert MLP: strict CUDA + Triton kernels deepseek-P5 DSv4 platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations)
#387 opened Sep 4, 2026 by jyizheng Loading…
4
[CI] Fix black formatting on main and pin line-length in pyproject.toml
#384 opened Sep 3, 2026 by Dnoob Contributor Loading…
1
4
[DSv4][P1-S0] Start kit for the P1 work package (mHC + RMSNorm) deepseek-P1 DSv4 platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations)
#383 opened Sep 3, 2026 by zhangj1an Collaborator Loading…
10 tasks
6
feat(ascend): add SwiGLU forward and backward kernels Ascend
#381 opened Sep 3, 2026 by erfgss Contributor Loading…
2
feat(ascend): add RoPE kernel Ascend
#378 opened Sep 2, 2026 by erfgss Contributor Loading…
9
Musa support native kernels
#376 opened Sep 1, 2026 by Arlo-mt • Draft
3
feat: enable Triton kernels on MUSA MUSA
#375 opened Sep 1, 2026 by Arlo-mt Loading…
6
docs(readme): update feature and platform support documentation Improvements or additions to documentation
#374 opened Sep 1, 2026 by Flink-ddd Collaborator Loading…
3
[skill] add ws1 ascend kernel Ascend
#373 opened Sep 1, 2026 by zhangj1an Collaborator Loading…
1
[WS1][Ascend] [Qwen3-8b] Fused linear logp ops Ascend
#372 opened Sep 1, 2026 by zhangj1an Collaborator Loading…
1
[WS1][Ascend] [Qwen3-8b] LM head ops Ascend
#371 opened Sep 1, 2026 by zhangj1an Collaborator Loading…
1
[WS1][Ascend] [Qwen3-8b] Fused logp ops Ascend
#370 opened Sep 1, 2026 by zhangj1an Collaborator Loading…
1
[WS1][Ascend] [Qwen3-8b] Embedding ops Ascend
#369 opened Sep 1, 2026 by zhangj1an Collaborator Loading…
7
[DSv4][P5-0] Start kit for the P5 work package (MXFP4 Routed Expert + LoRA + Shared Expert) deepseek-P5 DSv4 platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations)
#368 opened Sep 1, 2026 by KJLdefeated Collaborator Loading…
@KJLdefeated
7
[WS1] Add batch-invariant h_aggregate kernel deepseek-P1 DSv4 platform: cuda Specific optimizations or bugs in NVIDIA graphics cards (such as FlashInfer, TMA optimizations)
#366 opened Aug 30, 2026 by nodeeeeee Loading…
2
feat(ascend): add batch-invariant RMSNorm Ascend C operator Ascend
#364 opened Aug 30, 2026 by erfgss Contributor Loading…
9
docs: add DCO 1.1 text and contributor sign-off guide type: ci-cd Modify GitHub Actions, automated tests, and packaging/deployment tasks.
#359 opened Aug 29, 2026 by Zhifu-Liu Contributor Loading…
8
feat(ascend): add deterministic collective Ascend C kernel Ascend
#355 opened Aug 28, 2026 by zhangj1an Collaborator Loading…
1
feat(ascend): add prefix-shared attention Ascend C kernel Ascend
#340 opened Aug 25, 2026 by zhangj1an Collaborator Loading…
1
[WS1][kernels] Deterministic attention Ascend C kernel Ascend
#320 opened Aug 19, 2026 by zhangj1an Collaborator Loading…
2
ProTip! Add no:assignee to see everything that’s not assigned.