Commits · 254fd12cf407dbff61ec77250d834c8fb17422a6 · OpenDAS / TransformerEngine

13 Aug, 2025 3 commits
- Merge branch 'develop_v2.5' · 254fd12c
  wenjh authored Aug 13, 2025
  
  254fd12c
- Formatted · c6dae0e5
  wenjh authored Aug 13, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  c6dae0e5
- Delete tmpArgs in groupedgemm · 3cdceb87
  wenjh authored Aug 13, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  3cdceb87
12 Aug, 2025 2 commits
- Merge branch 'develop_v2.5' · 554296b4
  wenjh authored Aug 12, 2025
  
  554296b4
- Use hipMemcpy rather than hipMemcpyAsync · 1f97aebb
  wenjh authored Aug 12, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  1f97aebb
11 Aug, 2025 2 commits
- Merge branch 'develop_v2.5' · dcb27bde
  wenjh authored Aug 11, 2025
  
  dcb27bde
- Fix hipblaslt_goupedgemm · 8665c111
  wenjh authored Aug 11, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  8665c111
08 Aug, 2025 4 commits
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 0a0d309c
  yuguo authored Aug 08, 2025
  
  0a0d309c
- [DCU] add tmp_userArgs for blaslt groupgemm · 14aaa48a
  yuguo authored Aug 08, 2025
  
  14aaa48a
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · a61caafd
  yuguo authored Aug 08, 2025
  
  a61caafd
- [DCU] add NVTE_INT8_SIM_FP8_TENSORWISE · 3eb6ea62
  yuguo authored Aug 08, 2025
  
  3eb6ea62
07 Aug, 2025 2 commits
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · af196942
  yuguo authored Aug 07, 2025
  
  af196942
- [DCU] fix channelwise train accumulate bug · 68d6c506
  yuguo authored Aug 07, 2025
  
  68d6c506
06 Aug, 2025 6 commits
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · fb6798f1
  yuguo authored Aug 06, 2025
  
  fb6798f1
- [DCU] fix channelwise train oom bug · 4a013bd5
  yuguo authored Aug 06, 2025
  
  4a013bd5
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 468d9d2d
  yuguo authored Aug 06, 2025
  
  468d9d2d
- [DCU] userargs groupedgemm · ddfbdaf4
  yuguo authored Aug 06, 2025
  
  ddfbdaf4
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · eadb9886
  yuguo authored Aug 06, 2025
  
  eadb9886
- [DCU] fix batchlinear core dump in 2.5 · eac0d49b
  yuguo authored Aug 06, 2025
  
  eac0d49b
05 Aug, 2025 2 commits
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 6aafc95e
  yuguo authored Aug 05, 2025
  
  6aafc95e
- [DCU] fix all gather usage · d8041744
  yuguo authored Aug 05, 2025
  
  d8041744
31 Jul, 2025 2 commits
- Merge branch 'develop_v2.5' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · a9e430c0
  yuguo authored Jul 31, 2025
  
  a9e430c0
- [DCU] triton surpport e4m3_nv · a397dcb7
  yuguo authored Jul 31, 2025
  
  a397dcb7
29 Jul, 2025 1 commit
- Merge branch 'main' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 9ab6cd98
  yuguo authored Jul 29, 2025
  
  9ab6cd98
25 Jul, 2025 4 commits
- Merge branch 'develop_v2.4' · 84e8ce2f
  wenjh authored Jul 25, 2025
  
  84e8ce2f
- Disable lightop for now · ff1e14af
  wenjh authored Jul 25, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  ff1e14af
- Merge branch 'develop_v2.4' · cddbbf59
  wenjh authored Jul 25, 2025
  
  cddbbf59
- TN w8a8 lightop · 4088797f
  wenjh authored Jul 25, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  4088797f
22 Jul, 2025 3 commits
- [DCU] fix compile · 782f6092
  yuguo authored Jul 22, 2025
  
  782f6092
- [DCU] fix merge · eac75188
  yuguo authored Jul 22, 2025
  
  eac75188
- Merge commit '7a9a0825' of... · 44740c6c
  yuguo authored Jul 22, 2025
```
Merge commit '7a9a0825' of https://github.com/NVIDIA/TransformerEngine
```
  44740c6c
21 Jul, 2025 1 commit
- Changed VERSION to 2.7.0.dev0 (#1973) · 7a9a0825
  Kshitij Lakhani authored Jul 21, 2025
```
Signed-off-by: Kshitij Janardan Lakhani <klakhani@nvidia.com>
```
  7a9a0825
19 Jul, 2025 1 commit
- [JAX] Update tolerance of distributed layernorm MLP for FP8 (#1971) · ca7407e3
  jberchtold-nvidia authored Jul 18, 2025
```
Update tolerance of distributed layernorm MLP for FP8
Signed-off-by: Jeremy Berchtold <jberchtold@nvidia.com>
```
  ca7407e3
18 Jul, 2025 7 commits
- [Test] Enable cuDNN Norm tests in the CPP suite (#1957) · 86c50977
  Phuong Nguyen authored Jul 18, 2025
```
* enable cudnn norm tests
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>

* exclude tests on pre-Hopper
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>

---------
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
```
  86c50977
- [JAX] Set `precision=HIGHEST` for the ref_grouped_gemm impl in the unit test (#1967) · 2d4644b7
  Phuong Nguyen authored Jul 18, 2025
```
* set precision=HIGHEST for the ref_grouped_gemm impl in the unit test
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>


---------
Signed-off-by: Phuong Nguyen <phuonguyen@nvidia.com>
```
  2d4644b7
- Merge branch 'develop_v2.4' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 8113d9e0
  yuguo authored Jul 18, 2025
  
  8113d9e0
- [DCU] fix · d9847b6d
  yuguo authored Jul 18, 2025
  
  d9847b6d
- Merge branch 'develop_v2.4' of http://10.16.6.30/dcutoolkit/deeplearing/TransformerEngine · 93ecbc82
  yuguo authored Jul 18, 2025
  
  93ecbc82
- [DCU] fix bias gradient · 736e8f8b
  yuguo authored Jul 18, 2025
  
  736e8f8b
- Merge branch 'develop_v2.4' · bb8cf71b
  wenjh authored Jul 18, 2025
  
  bb8cf71b