Skip to content

Pull requests: NVIDIA/TransformerEngine

New pull request New
62 Open 1,063 Closed
62 Open 1,063 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Use internal quantizer for input to the modules
#1551 opened Mar 7, 2025 by ptrendx Loading…
2 of 13 tasks
2
Disable parallelism in core build test testing Improvements to tests or testing infrastructure
#1550 opened Mar 7, 2025 by timmoon10 Loading…
7 of 14 tasks
1
change softmax_lse correction of CP to FP32
#1546 opened Mar 7, 2025 by xrennvidia Loading…
6 of 13 tasks
1
Subchannel Block quantized GEMM
#1545 opened Mar 6, 2025 by kwyss-nvidia Loading…
6 of 12 tasks
[PyTorch] Draft: Enable fp8_primary_weights for current scaling
#1544 opened Mar 6, 2025 by kunlunl Loading…
13 tasks
Refactoring attention.py
#1542 opened Mar 6, 2025 by KshitijLakhani • Draft
13 tasks
@KshitijLakhani
Remove xla_ignore_channel_id check and ignore Scan loop warning in un…
#1540 opened Mar 6, 2025 by zlsh80826 Loading…
8 of 13 tasks
2
Fused Linear and Cross Entropy operations
#1537 opened Mar 5, 2025 by Jianbing-D Loading…
2
Parallelize CPU reference implementation in tests testing Improvements to tests or testing infrastructure
#1534 opened Mar 4, 2025 by negvet Loading…
8 of 14 tasks
9
Blackwell devel commoverlap mlperftests
#1529 opened Feb 28, 2025 by vasunvidia Loading…
12 tasks
1
Enable MXFP8 for Grouped Linear
#1525 opened Feb 28, 2025 by yaox12 Loading…
4 of 16 tasks
6
[PyTorch] Remove Megatron-LM convergence test 2.2.0 testing Improvements to tests or testing infrastructure
#1521 opened Feb 28, 2025 by timmoon10 Loading…
7 of 13 tasks
3
Blockwise float8 quantizer and quantized tensor class
#1513 opened Feb 27, 2025 by kwyss-nvidia Loading…
18 of 34 tasks
12
Draft: split wgrad poc
#1510 opened Feb 26, 2025 by lhb8125 • Draft
13 tasks
Support tensors with only column-wise data enhancement New feature or request performance
#1505 opened Feb 25, 2025 by timmoon10 Loading…
7 of 13 tasks
1
[Pytorch] Dynamo ONNX export support
#1497 opened Feb 19, 2025 by pggPL Loading…
8 of 13 tasks
6
Explicitly use python3 and pip3 executables testing Improvements to tests or testing infrastructure
#1486 opened Feb 15, 2025 by timmoon10 Loading…
8 of 13 tasks
2
RoPE enhancements
#1478 opened Feb 11, 2025 by sudhakarsingh27 Loading…
3 of 6 tasks
@sudhakarsingh27
support adam bf16 state
#1465 opened Feb 8, 2025 by XiaobingSuper Loading…
6 of 13 tasks
3
[PyTorch] Enable quantized activation backward kernels in operation-based API tests testing Improvements to tests or testing infrastructure
#1463 opened Feb 7, 2025 by timmoon10 Loading…
6 of 14 tasks
1
[Pytorch] Nvidia-DLFramework-Inspect support
#1441 opened Jan 30, 2025 by pggPL Loading…
8 of 14 tasks
32
Introduce NVSHMEM based communication API for pytorch
#1430 opened Jan 28, 2025 by gdengk Loading…
13 tasks
[PyTorch] cuBLAS workspace size fix for TP overlap unit test bug Something isn't working
#1415 opened Jan 17, 2025 by denera Loading…
8 of 13 tasks
1
@denera
4
Fix Linear Weight Initialization in the PaddlePaddle Implementation
#1413 opened Jan 17, 2025 by GuoxiaWang Loading…
4 of 13 tasks
Better cuBLAS handle management
#1389 opened Jan 2, 2025 by ptrendx Loading…
8 of 13 tasks
1
@ksivaman
8
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.