Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
100 Open 1,766 Closed
100 Open 1,766 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

Cpu optimizations v2 cpu_overhead
#2514 opened Dec 12, 2025 by vthumbe1503 • Draft
13 tasks
Testing v2.6 + pr2201
#2513 opened Dec 12, 2025 by KshitijLakhani • Draft
13 tasks
[Common] Optimize fused RoPE kernel performance performance Performance issues
#2508 opened Dec 11, 2025 by yaox12 • Draft
13 tasks
[PyTorch debug] Fix test for debug tools
#2507 opened Dec 11, 2025 by pggPL Loading…
8 of 13 tasks
5
Check calling convention for amax switch.
#2506 opened Dec 11, 2025 by kwyss-nvidia Loading…
6 of 13 tasks
8
[common] Add support for cuBLASLt GEMM for GroupedTensor MoE
#2502 opened Dec 10, 2025 by pggPL Loading…
8 tasks done
1
6
Add logic for block-scaled tensors with GEMM swizzled scales enhancement New feature or request refactor
#2486 opened Dec 6, 2025 by timmoon10 Loading…
14 of 19 tasks
1
11
[JAX] Remove unused TE DPA module dtype which fixes cuDNN backend detection to properly use input dtypes
#2485 opened Dec 5, 2025 by jberchtold-nvidia Loading…
8 of 13 tasks
6
[JAX] Estimate post-RHT amax using regular amax fp4
#2479 opened Dec 4, 2025 by jberchtold-nvidia • Draft
13 tasks
2
Add support for SWA (left, right) with FusedAttention 2.11.0
#2477 opened Dec 4, 2025 by sudhakarsingh27 Loading…
22 of 28 tasks
28
fix ce loss calculation when some tokens are ignored bug Something isn't working
#2476 opened Dec 4, 2025 by yashaswikarnati Loading…
1 of 13 tasks
23
[JAX] Einsum with quantization
#2474 opened Dec 3, 2025 by phu0ngng • Draft
13 tasks
[PyTorch] Documentation for op fuser API documentation Improvements or additions to documentation
#2447 opened Dec 3, 2025 by timmoon10 Loading…
8 of 13 tasks
11
Fix transformer 2.9.0 (torch 2.9.1 used by SGLang 0.5.5) build
#2445 opened Dec 2, 2025 by yiakwy-xpu-ml-framework-team Loading…
13 tasks
4
Add ccache support to TE and use it in GitHub actions build Build system
#2444 opened Dec 2, 2025 by ptrendx • Draft
1 of 6 tasks
[Common] Comm+GEMM overlap API updated to support cuBlasMp backend (incl. framework API)
#2443 opened Dec 2, 2025 by denera • Draft
4 of 13 tasks
@denera
3
[PyTorch] Enable post-RHT amax estimation fp4
#2442 opened Dec 2, 2025 by negvet • Draft
1 of 13 tasks
10
[JAX] Better error message when Q, K, V are sharded differently
#2440 opened Dec 2, 2025 by jberchtold-nvidia Loading…
8 of 13 tasks
8
[pyTorch] CPU performance optimizations cpu_overhead
#2439 opened Dec 1, 2025 by ptrendx • Draft
13 tasks
9
support cuda graph capture offloading module
#2435 opened Dec 1, 2025 by lhb8125 • Draft
13 tasks
5
[PyTorch] Add FA4 Support
#2432 opened Nov 28, 2025 by yaox12 • Draft
1 of 16 tasks
6
Fix FusedAdam DTensor compatibility issue
#2425 opened Nov 26, 2025 by shjwudp Loading…
13 tasks
1
3
[JAX] Add tutorial for integrating TE/JAX quantization into an existing framework
#2423 opened Nov 26, 2025 by jberchtold-nvidia Loading…
8 of 13 tasks
25
[JAX] Wrapper for Permutation Triton kernel MoE
#2419 opened Nov 25, 2025 by tdophung • Draft
9 of 16 tasks
@tdophung
6
[Common] Add kFloat64 partial support
#2417 opened Nov 24, 2025 by phu0ngng Loading…
7 of 13 tasks
11
ProTip! Exclude everything labeled bug with -label:bug.