Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
76 Open 1,351 Closed
76 Open 1,351 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] Optimize the performance of permute fusion kernels
#1927 opened Jul 4, 2025 by hxbai Loading…
7 of 13 tasks
[PyTorch] Fix setting align_size when FP8 is not initialized
#1926 opened Jul 4, 2025 by yaox12 Loading…
1 of 13 tasks
1
[JAX] Fix grouped GEMM error on CUDA 12.9.1 & later
#1925 opened Jul 3, 2025 by huanghua1994 Loading…
6 of 13 tasks
2
Add test for LayerNormMLP implementation using te.ops.Sequential to test_fusible_ops.py
#1924 opened Jul 3, 2025 by janekb04 Loading…
6 of 13 tasks
5
[PyTorch] Fuse permute+pad and unpermute+unpad ops for FP8 optimization
#1921 opened Jul 3, 2025 by xiaoxi-wangfj Loading…
3 of 12 tasks
Call pre_(first_)forward only when global state changes
#1917 opened Jul 1, 2025 by janekb04 Loading…
7 of 13 tasks
9
[JAX] Resolve test conflict in JAX helper tests
#1916 opened Jul 1, 2025 by emmanuel-ferdman Loading…
6 of 13 tasks
[Common] Optimize KV cache related kernels
#1914 opened Jun 30, 2025 by cyanguwa Loading…
8 of 13 tasks
1
Fix import error when flash attention 3 is installed
#1913 opened Jun 30, 2025 by HollowMan6 Loading…
7 of 13 tasks
[PyTorch] Optimize create_tensor in quantizer
#1912 opened Jun 30, 2025 by yaox12 • Draft
13 tasks
3
[PyTorch debug] Improve precision debug tools performance
#1909 opened Jun 30, 2025 by pggPL Loading…
9 of 13 tasks
3
[PyTorch debug] Run test_sanity with debug tools enabled.
#1908 opened Jun 30, 2025 by pggPL Loading…
7 of 13 tasks
6
[PyTorch] Support FA3 MLA CP feature
#1907 opened Jun 28, 2025 by zhujian19891203 Loading…
7 of 13 tasks
@cyanguwa
[PyTorch Debug] Support log fp8 tensor stats for blockwise recipe
#1905 opened Jun 27, 2025 by lengerfulluse Loading…
12 tasks
[common] NVFP4 kernels enhancement New feature or request
#1904 opened Jun 27, 2025 by Oleg-Goncharov • Draft
5 of 13 tasks
Fix fp8_calibration path
#1903 opened Jun 27, 2025 by sudhakarsingh27 • Draft
1 of 13 tasks
@sudhakarsingh27
[JAX] Update distributed LayerNormMLP test tolerance for L40
#1901 opened Jun 26, 2025 by jberchtold-nvidia Loading…
8 of 13 tasks
2
[PyTorch] Tests for loading previously-generated checkpoints testing Improvements to tests or testing infrastructure
#1899 opened Jun 26, 2025 by timmoon10 Loading…
8 of 14 tasks
2
[PyTorch Debug] More advanced stats for Quantized Tensors
#1897 opened Jun 26, 2025 by pggPL Loading…
2 of 13 tasks
Handle dtypes more carefully in multi-tensor Adam bug Something isn't working
#1888 opened Jun 17, 2025 by timmoon10 Loading…
6 of 13 tasks
1
[Pytorch] CP + THD + chunked attention support.
#1887 opened Jun 17, 2025 by pggPL • Draft
1 of 13 tasks
pipeline aware cpu offload
#1886 opened Jun 17, 2025 by liuzhenhai93 Loading…
8 tasks done
3
Tongliu/router fusion
#1883 opened Jun 16, 2025 by Autumn1998 Loading…
13 tasks
8
[PyTorch] Limit max time for distributed PyTorch tests testing Improvements to tests or testing infrastructure
#1877 opened Jun 13, 2025 by timmoon10 Loading…
6 of 14 tasks
5
[PyTorch] Add save_original_input in Linear/GroupedLinear to save memory
#1865 opened Jun 11, 2025 by hxbai Loading…
8 of 13 tasks
1
ProTip! no:milestone will show everything without a milestone.