Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
31 Open 621 Closed
31 Open 621 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add documentation for dot product attention
#889 opened Jun 4, 2024 by cyanguwa Loading…
2 of 4 tasks
6
Get CMake bin dir from CMake module if possible bug Something isn't working build Build system
#888 opened Jun 4, 2024 by timmoon10 Loading…
3 of 11 tasks
1
Use unoptimized RMSNorm kernel if pointers are not aligned bug Something isn't working
#886 opened Jun 3, 2024 by timmoon10 Loading…
4 of 11 tasks
2
[PyTorch] Add support for cuDNN FusedAttention + THD + CP
#885 opened Jun 3, 2024 by xrennvidia Loading…
6 tasks
15
[JAX] Splitting CPP extensions by category
#883 opened Jun 1, 2024 by phu0ngng Loading…
5 of 11 tasks
2
Fp8 model init factory
#880 opened May 30, 2024 by sudhakarsingh27 • Draft
3
[JAX] Added unit tests for distributed LayernormMLP
#878 opened May 29, 2024 by phu0ngng Loading…
4 of 9 tasks
5
Build system refactor for wheels
#877 opened May 29, 2024 by ksivaman Loading…
8 of 11 tasks
@ksivaman
33
[PyTorch] Avoid select op in PyTorch extensions enhancement New feature or request
#865 opened May 24, 2024 by timmoon10 Loading…
6 of 11 tasks
3
Avoid framework specific import from top level enhancement New feature or request
#862 opened May 22, 2024 by ksivaman • Draft
6 of 11 tasks
@ksivaman
1
[C/PyTorch/JAX] Build system improvements for rpath and C++11 ABI build Build system enhancement New feature or request
#858 opened May 20, 2024 by denera Loading…
9 of 11 tasks
@denera
26
[Common/PyTorch] Grouped GEMM via multi-stream cuBLAS
#853 opened May 17, 2024 by yaox12 Loading…
8 of 11 tasks
18
[JAX] Rewrite the Format of FP8 Meta and Remove unused ShardingTypes.
#842 opened May 13, 2024 by mingxu1067 Loading…
8 of 11 tasks
25
Generation tutorial for Gemma model
#829 opened May 1, 2024 by pggPL Loading…
8 of 11 tasks
33
[Pytorch] Implement fp32 accumulation for attention with context parallel in both forward and backward pass.
#821 opened Apr 28, 2024 by Yuxin-CV Loading…
1
[UB] Adding support for multinode nvlink
#815 opened Apr 26, 2024 by shamisp Loading…
2
Bug fix in DGRAD->RS overlap
#802 opened Apr 23, 2024 by vasunvidia • Draft
[JAX] POC of custom call selection
#797 opened Apr 22, 2024 by zlsh80826 • Draft
3
[PyTorch] Fix minor bug in computing num_gqa_groups_per_partition bug Something isn't working
#777 opened Apr 13, 2024 by knowlsie Loading…
4
[C/PyTorch] Refactor and move userbuffers into TE/common
#760 opened Apr 8, 2024 by denera Loading…
6 of 13 tasks
1
@denera
43
Fix bhss bias format before sm90
#736 opened Mar 27, 2024 by zlsh80826 Loading…
3
[PyTorch] Sequential fuser enhancement New feature or request
#707 opened Mar 9, 2024 by timmoon10 Loading…
2 of 6 tasks
3
[PyTorch] Distributed intermediate/activation tensors for FSDP
#687 opened Feb 28, 2024 by denera Loading…
@denera
13
[PyTorch] Re-enable bias+GELU fusion for non-reentrant checkpointing -- WIP
#686 opened Feb 27, 2024 by denera • Draft
@denera
1
Remove now useless padding as it is now down automatically. jax
#680 opened Feb 25, 2024 by nouiz Loading…
12
ProTip! Follow long discussions with comments:>50.