Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
190 Open 2,476 Closed
190 Open 2,476 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

[PyTorch] Schedule delayed-scaling updates after backward
#3456 opened Sep 1, 2026 by pggPL Collaborator • Draft
9 of 13 tasks
[PyTorch] Deprecate unused is_cg_capturable in parallel_cross_entropy 2.19
#3455 opened Sep 1, 2026 by pggPL Collaborator Loading…
5 of 13 tasks
2
[Common] row-scaled nvfp4 path: fuse row/col amax into a single TMA-tiled kernel community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3454 opened Sep 1, 2026 by cael-ling Contributor Loading…
2 of 13 tasks
2
Attribute and retry transient CP pool NaNs 2.19
#3453 opened Sep 1, 2026 by sudhakarsingh27 Member Loading…
7 of 12 tasks
2
[JAX] Add EP borrowed-comm path via XLA FFI collectives extension
#3452 opened Aug 31, 2026 by phu0ngng Collaborator • Draft
13 tasks
Bump NCCL-EP submodule commit
#3451 opened Aug 31, 2026 by phu0ngng Collaborator Loading…
13 tasks
2
Misc docs rendering fixes 2.19
#3450 opened Aug 31, 2026 by ksivaman Member Loading…
13 tasks
2
[JAX] Add sqrtsoftplus router score function
#3448 opened Aug 31, 2026 by jberchtold-nvidia Collaborator • Draft
8 of 13 tasks
2
[JAX] Attention support for explicit sharding
#3446 opened Aug 31, 2026 by jberchtold-nvidia Collaborator • Draft
8 of 13 tasks
1
Cutlass Upgrade to 4.8 2.20
#3443 opened Aug 31, 2026 by vthumbe1503 Collaborator Loading…
13 tasks
3
[Common] Reduce default cfg's SMEM usage for mhc triton kernel 2.19
#3442 opened Aug 28, 2026 by kainzhong Collaborator Loading…
8 of 13 tasks
2
[Core] Fix L40 cublas heuristics 2.20
#3440 opened Aug 28, 2026 by jberchtold-nvidia Collaborator Loading…
13 tasks done
5
[Common] Let MXFP8 quantization always reduce dbias in colwise
#3439 opened Aug 28, 2026 by kainzhong Collaborator Loading…
8 of 13 tasks
2
Relax runtime checks for activation recompute into Warnings community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3436 opened Aug 28, 2026 by ghadiaravi13 Contributor • Draft
1 of 13 tasks
2
[Common] Split grouped activation build community-contribution PRs from external contributor outside the core maintainers, representing community-driven work. org-contribution
#3430 opened Aug 27, 2026 by harryzhou2000 Contributor Loading…
2
[PyTorch] Reduce CUDA graph memory retention community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3427 opened Aug 26, 2026 by buptzyb Contributor Loading…
@ksivaman
6
[PyTorch] Fix mutable QB bounds in CUDA graphs org-contribution
#3426 opened Aug 26, 2026 by harryzhou2000 Contributor Loading…
6
Support paged stashing for GroupedLinear activations community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3423 opened Aug 25, 2026 by lhb8125 Contributor Loading…
1
Fix: fused QUproj + RoPE + Quant community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3421 opened Aug 24, 2026 by ghadiaravi13 Contributor Loading…
13 tasks
3
[PyTorch] Allow CP P2P transport group overrides community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3420 opened Aug 24, 2026 by xiaoyao0115 • Draft
[PyTorch] Bound FusedAdam tensor-handle usage community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3418 opened Aug 23, 2026 by zupengwang Loading…
1
[Common] Fix TMA synchronization in quantization kernels
#3417 opened Aug 22, 2026 by Oleg-Goncharov Collaborator Loading…
6 of 13 tasks
3
Ring Attention: free unused kv comm buffers community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3411 opened Aug 21, 2026 by francesco-bertolotti Contributor Loading…
6 of 13 tasks
2
Reduce Grouped MLP Fuser CPU Overhead community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#3410 opened Aug 20, 2026 by zhongbozhu Collaborator Loading…
13 tasks
12
[Common] Benchmarkable Unit Tests
#3408 opened Aug 19, 2026 by denera Collaborator • Draft
8 of 13 tasks
@denera
1
ProTip! Adding no:label will show everything without a label.