Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
101 Open 1,784 Closed
101 Open 1,784 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

Refactor and trim TE JAX Attn testing
#2542 opened Dec 24, 2025 by KshitijLakhani • Draft
13 tasks
Solve pytorch-triton and triton package contention
#2540 opened Dec 23, 2025 by tdophung Loading…
8 of 13 tasks
4
[PyT] Plumbing correct bias dims from TE to cudnn attention bug Something isn't working pytorch
#2537 opened Dec 20, 2025 by KshitijLakhani Loading…
4 of 11 tasks
@KshitijLakhani
4
[PyTorch] Bunch of fixes for cpu offloading
#2535 opened Dec 19, 2025 by pggPL • Draft
13 tasks
1
[docs] Getting started refactor documentation Improvements or additions to documentation
#2534 opened Dec 18, 2025 by pggPL Loading…
8 of 13 tasks
2
[DO NOT MERGE] Get seqlens and offsets in O(N) space instead of O(N*N) space do not merge
#2530 opened Dec 17, 2025 by KshitijLakhani • Draft
13 tasks
@KshitijLakhani
[JAX] Fix incorrect calculation of segment pos from segment ids in user-facing API attention bug Something isn't working jax
#2523 opened Dec 16, 2025 by KshitijLakhani Loading…
5 of 13 tasks
@KshitijLakhani
14
[JAX] Calculate seqlens and offsets in O(N) space instead of O(N*N) space for THD sequences attention
#2522 opened Dec 16, 2025 by KshitijLakhani • Draft
13 tasks
@KshitijLakhani
Enable post-RHT amax estimation with separate amax scale kernel fp4
#2521 opened Dec 16, 2025 by negvet • Draft
13 tasks
1
Documentation for cpu offloading documentation Improvements or additions to documentation
#2520 opened Dec 16, 2025 by pggPL Loading…
8 of 13 tasks
2
[PyTorch] Support cudagraph recomputation
#2518 opened Dec 16, 2025 by buptzyb Loading…
1 of 13 tasks
4
[JAX] HLO FFI tests jax
#2517 opened Dec 16, 2025 by jberchtold-nvidia Loading…
7 of 13 tasks
11
Cpu optimizations v2 cpu_overhead
#2514 opened Dec 12, 2025 by vthumbe1503 • Draft
13 tasks
[DO NOT MERGE] Testing v2.6 + pr2201 attention
#2513 opened Dec 12, 2025 by KshitijLakhani • Draft
13 tasks
@KshitijLakhani
[Common] Optimize fused RoPE kernel performance performance Performance issues
#2508 opened Dec 11, 2025 by yaox12 • Draft
13 tasks
[common] Add support for cuBLASLt GEMM for GroupedTensor MoE
#2502 opened Dec 10, 2025 by pggPL Loading…
8 tasks done
1
23
Add logic for block-scaled tensors with GEMM swizzled scales enhancement New feature or request MoE performance Performance issues refactor
#2486 opened Dec 6, 2025 by timmoon10 Loading…
14 of 19 tasks
1
15
[JAX] Estimate post-RHT amax using regular amax fp4
#2479 opened Dec 4, 2025 by jberchtold-nvidia • Draft
13 tasks
2
Add support for SWA (left, right) with FusedAttention 2.12.0
#2477 opened Dec 4, 2025 by sudhakarsingh27 Loading…
22 of 28 tasks
35
[JAX] Einsum with quantization
#2474 opened Dec 3, 2025 by phu0ngng • Draft
13 tasks
[PyTorch] Documentation for op fuser API documentation Improvements or additions to documentation
#2447 opened Dec 3, 2025 by timmoon10 Loading…
8 of 13 tasks
14
Fix transformer 2.9.0 (torch 2.9.1 used by SGLang 0.5.5) build
#2445 opened Dec 2, 2025 by yiakwy-xpu-ml-framework-team Loading…
13 tasks
4
[Common] Comm+GEMM overlap API updated to support cuBlasMp backend (incl. framework API)
#2443 opened Dec 2, 2025 by denera Loading…
5 of 13 tasks
@denera
9
[PyTorch] Enable post-RHT amax estimation fp4
#2442 opened Dec 2, 2025 by negvet • Draft
1 of 13 tasks
10
[JAX] Better error message when Q, K, V are sharded differently attention jax
#2440 opened Dec 2, 2025 by jberchtold-nvidia Loading…
8 of 13 tasks
8
ProTip! Follow long discussions with comments:>50.