Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
126 Open 1,888 Closed
126 Open 1,888 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

[Common][PyTorch] Add z_loss_weight and log_sum_exp output to parallel_cross_entropy
#2707 opened Feb 26, 2026 by bassoy • Draft
8 tasks done
[Draft] Newton-Schulz via cuSOLVERMp
#2706 opened Feb 25, 2026 by vcherepanov-nv Loading…
6 of 13 tasks
12
[All] Added better error messages
#2705 opened Feb 25, 2026 by ptrendx Loading…
7
Fix Flash Attention 3 API compatibility for window size parameters 2.14.0
#2704 opened Feb 25, 2026 by jhvmhg Loading…
3 of 13 tasks
10
[JAX] Deprecate GSPMD: remove infer_sharding_from_operands and GSPMD tests
#2702 opened Feb 24, 2026 by phu0ngng Loading…
8 of 13 tasks
6
[Draft][PyTorch] torch.compile support for TE Linear
#2701 opened Feb 24, 2026 by pggPL • Draft
13 tasks
Add fused_adam, quantized_model_init, and fsdp2 example
#2698 opened Feb 22, 2026 by pstjohn Loading…
1
8
[PyTorch] Zero-initialize learnable softmax_offset in DotProductAttention
#2694 opened Feb 20, 2026 by fjosw Loading…
7 of 13 tasks
4
Enable sm120 support for fused attn if cuDNN is 9.18.1+
#2693 opened Feb 20, 2026 by KshitijLakhani • Draft
13 tasks
[JAX] Fix batcher in FusedAttn primitive for when seg ids bdims != seg pos bdims 2.14.0
#2692 opened Feb 19, 2026 by KshitijLakhani Loading…
6 of 13 tasks
1
@KshitijLakhani
13
NVFP4 primary weight support
#2691 opened Feb 19, 2026 by WanZzzzzz Loading…
10 of 13 tasks
43
[PyTorch] Error out if constructing LayerNormLinear with row tensor parallelism bug Something isn't working
#2688 opened Feb 17, 2026 by timmoon10 Loading…
6 of 13 tasks
7
[PyTorch] torch.compile support for permutation functions
#2686 opened Feb 17, 2026 by pggPL Loading…
9 of 13 tasks
19
[Common] Remove volatile keyword in fused router kernel utils
#2683 opened Feb 13, 2026 by denera Loading…
8 of 13 tasks
@denera
3
[JAX] Integrate BF16 Grouped GEMM with on-device group sizes
#2680 opened Feb 13, 2026 by jberchtold-nvidia Loading…
8 of 13 tasks
1
16
[PyTorch][Fused Attn] Add support for cuDNN to return Softmax Stats always and Max when return_max_logit=True
#2677 opened Feb 12, 2026 by sudhakarsingh27 Loading…
7 of 13 tasks
27
[PyTorch] Add dtype information to QuantizedTensorStorage class
#2676 opened Feb 12, 2026 by ptrendx Loading…
1 of 13 tasks
14
[Common] MOE Split dBias cpu_overhead enhancement New feature or request MoE
#2674 opened Feb 11, 2026 by Oleg-Goncharov Loading…
8 of 13 tasks
17
Cherry pick "Adds dst.dtype information in copy_ method of quantized tensors. #2120"
#2673 opened Feb 11, 2026 by ptrendx Loading…
13 tasks
4
Fix and harden attention benchmark script
#2671 opened Feb 10, 2026 by KshitijLakhani • Draft
13 tasks
@KshitijLakhani
Fix nvfp4 convert_and_update_tensor shape check
#2670 opened Feb 10, 2026 by skydoorkai Loading…
13 tasks
1
13
Pytorch binding for cublas gemm + Grouped Linear integration
#2669 opened Feb 10, 2026 by vthumbe1503 • Draft
13 tasks
[pyTorch] Replace the make_empty implementation to use C++ implementation
#2666 opened Feb 10, 2026 by ptrendx Loading…
1 of 13 tasks
6
Improve handling of the NVTE_CUDA_ARCHS
#2665 opened Feb 9, 2026 by ptrendx Loading…
1 of 13 tasks
14
Add multi-precision training support to FSDP script
#2662 opened Feb 9, 2026 by aagallo Loading…
6 of 13 tasks
26
ProTip! Add no:assignee to see everything that’s not assigned.