Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
109 Open 1,970 Closed
109 Open 1,970 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

[Core] Fix MXFP8 grouped quantize for zero-sized groups in update_tma_descriptors 2.14.0 bug Something isn't working
#2782 opened Mar 18, 2026 by jberchtold-nvidia Loading…
8 of 13 tasks
1
3
[PyT] Install pytest in onnx L1 test as Pyt container no longer packages it 2.14.0
#2781 opened Mar 18, 2026 by KshitijLakhani Loading…
4 of 13 tasks
@KshitijLakhani
3
Fused Adam Support for MXFP8 + FSDP2 integration
#2780 opened Mar 18, 2026 by vthumbe1503 Loading…
13 tasks
9
Enable fused RMSNorm dLN + add through CUDNN
#2778 opened Mar 18, 2026 by CarlosGomes98 Loading…
1 of 13 tasks
8
[fused_router][pytorch] Optimize naive topk path and add perf benchmark
#2776 opened Mar 18, 2026 by XiaomingFun233 Loading…
6
add blackwell support filter for 9.7<=cudnn<9.18.1 2.14.0
#2775 opened Mar 17, 2026 by sudhakarsingh27 Loading…
13 tasks
6
[PyTorch] Add an API restore from function context to ensure tensors are detached
#2772 opened Mar 17, 2026 by kainzhong Loading…
7 of 13 tasks
5
add mark_not_offload() interface for cpu_offload_v1
#2770 opened Mar 17, 2026 by lhb8125 Loading…
13 tasks
4
GEMM + Swiglu fused Grouped MLP for MXFP8 2.14.0 MoE
#2769 opened Mar 17, 2026 by ksivaman Loading…
13 tasks
32
[Draft]Support for score_mod and score_mod_bprop in cuDNN's sdpa
#2767 opened Mar 16, 2026 by vcherepanov-nv Loading…
2 of 13 tasks
4
Fix the retrieval of overwrite_main_grad
#2764 opened Mar 16, 2026 by shjwudp • Draft
13 tasks
3
[JAX] MXFP8 Grouped GEMM
#2763 opened Mar 14, 2026 by jberchtold-nvidia • Draft
13 tasks
3
[JAX] MXFP8 Grouped Quantize V2
#2760 opened Mar 13, 2026 by jberchtold-nvidia • Draft
13 tasks
4
[PyTorch] transformer_engine.pytorch.autocast suport inside torch.compile
#2759 opened Mar 13, 2026 by pggPL Loading…
4 of 26 tasks
2
[Common] Improved fused MoE aux loss kernel for large # of experts 2.15 MoE
#2758 opened Mar 13, 2026 by denera • Draft
4 of 13 tasks
@denera
[JAX] Grouped GEMM Refactor to use first_dims and last_dims
#2749 opened Mar 10, 2026 by jberchtold-nvidia Loading…
1 of 13 tasks
25
[Common] Persistent Grouped NVFP4 quantization kernel
#2743 opened Mar 6, 2026 by Oleg-Goncharov • Draft
8 of 13 tasks
30
[Common] Persistent Grouped MXFP8 quantization kernel enhancement New feature or request MoE
#2738 opened Mar 5, 2026 by Oleg-Goncharov Loading…
9 of 13 tasks
21
Feat/cp nvshmem enhanced community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#2737 opened Mar 5, 2026 by Knight-of-Thunder Loading…
1 of 13 tasks
15
Feature/unswizzle community-contribution PRs from external contributor outside the core maintainers, representing community-driven work.
#2732 opened Mar 4, 2026 by int-smart Loading…
9 of 13 tasks
37
fix: scope get_full_cu_seqlens cache key by device and inference mode
#2728 opened Mar 3, 2026 by DmCarpe93 Loading…
8 of 13 tasks
4
[CI] Refactor CI build on GitHub
#2723 opened Mar 2, 2026 by ptrendx Loading…
1 of 13 tasks
11
[Common, pyTorch] Grouped MXFP8 dequantize support
#2722 opened Mar 2, 2026 by ptrendx Loading…
1 of 13 tasks
1
2
Add MXFP8 attention
#2719 opened Mar 1, 2026 by cyanguwa • Draft
13 tasks
10
[PyTorch] Fix CPU offloading for bulk-allocated quantized tensors
#2716 opened Feb 27, 2026 by lhb8125 • Draft
1 of 13 tasks
6
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.