Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
66 Open 1,454 Closed
66 Open 1,454 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] Quantizer as API
#2039 opened Aug 7, 2025 by negvet Loading…
5 of 11 tasks
3
Ubnext
#2038 opened Aug 6, 2025 by nv-akorzh Loading…
Symmetric Memory Pool
#2037 opened Aug 6, 2025 by wdykas Loading…
13 tasks
[JAX] TE Gemm custom call clean up
#2030 opened Aug 5, 2025 by phu0ngng Loading…
4 of 13 tasks
8
Add backward RMSNorm+Add fusion
#2028 opened Aug 5, 2025 by janekb04 Loading…
8 of 13 tasks
6
[PyTorch] Register weight and bias params in linear op bug Something isn't working
#2027 opened Aug 4, 2025 by timmoon10 Loading…
6 of 13 tasks
2
Offloading support for multiple attention layouts
#2024 opened Aug 3, 2025 by sanandaraj5597 Loading…
[PyTorch] Fix bug when deducing dtype in linear functional API bug Something isn't working
#2017 opened Aug 1, 2025 by timmoon10 Loading…
6 of 13 tasks
1
1
Dropout with 8-bit RNG
#2014 opened Jul 30, 2025 by vasunvidia Loading…
13 tasks
24
[Draft] Add FP8 attention with current scaling
#2012 opened Jul 30, 2025 by cyanguwa Loading…
8 of 13 tasks
[PyTorch] Disable fused dbias-quantize kernel for unsupported recipes bug Something isn't working
#2007 opened Jul 30, 2025 by timmoon10 Loading…
6 of 13 tasks
3
Remove if-else and torch.tensor to meet cudagraph requirement
#1997 opened Jul 25, 2025 by katec846 Loading…
13 tasks
4
Use userbuffers for MXFP8 wgrad all-gather overlap
#1982 opened Jul 22, 2025 by djns99 Loading…
1 of 13 tasks
11
[C][PyTorch] NVFP4 forward MXFP8 backward recipe
#1970 opened Jul 18, 2025 by ksivaman • Draft
2 of 13 tasks
16
[PyTorch][Mcore] Fix illegal memory access issue while using Mcore async checkpoint with fp8 tensorwise recipe bug Something isn't working
#1956 opened Jul 16, 2025 by zhongbozhu Loading…
13 tasks
2
[PyTorch Debug] Debug support for GroupedLinear
#1953 opened Jul 15, 2025 by pggPL • Draft
13 tasks
[PyTorch] Support delay_wgrad_compute cudagraph
#1948 opened Jul 14, 2025 by buptzyb Loading…
2 of 13 tasks
[PyTorch] Fuse permute+pad and unpermute+unpad ops for FP8 optimization
#1921 opened Jul 3, 2025 by xiaoxi-wangfj Loading…
3 of 12 tasks
3
Fix import error when flash attention 3 is installed
#1913 opened Jun 30, 2025 by HollowMan6 Loading…
7 of 13 tasks
1
[PyTorch debug] Improve precision debug tools performance
#1909 opened Jun 30, 2025 by pggPL Loading…
9 of 13 tasks
56
[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
[PyTorch Debug] More advanced stats for Quantized Tensors
#1897 opened Jun 26, 2025 by pggPL Loading…
2 of 13 tasks
9
ProTip! Mix and match filters to narrow down what you’re looking for.