Commits · e4f5325ef4a2ee2edcbb688fdaa9ef9741227ecb · OpenDAS / TransformerEngine

24 Feb, 2026 2 commits
- Merge branch 'develop_v2.10' into release_v2.10 · e4f5325e
  wenjh authored Feb 24, 2026
  
  e4f5325e
- Enable fp8 on nmz · a68e5f87
  wenjh authored Feb 24, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  a68e5f87
04 Feb, 2026 4 commits
- Merge branch 'develop_v2.10' into release_v2.10 · eebc98fc
  wenjh authored Feb 04, 2026
  
  eebc98fc
- Fix undefined use_int8 error · 99a1c744
  wenjh authored Feb 04, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  99a1c744
- Merge branch 'develop_v2.10' into release_v2.10 · d8c4e220
  wenjh authored Feb 04, 2026
  
  d8c4e220
- Remove dump code of tensorwise_int8_bgrad_kernel · 2bb532fb
  wenjh authored Feb 04, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  2bb532fb
30 Jan, 2026 2 commits
- Merge branch 'develop_v2.10' into release_v2.10 · d954fc54
  wenjh authored Jan 30, 2026
  
  d954fc54
- Fix out-of-bounds issues for types struct in common/common.h · d2c77acc
  wenjh authored Jan 30, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  d2c77acc
23 Jan, 2026 8 commits
- Merge branch 'develop_v2.10' into release_v2.10 · aeceeac0
  wenjh authored Jan 23, 2026
  
  aeceeac0
- Fix issues related to L1cpp tests · 284d3f6f
  maxiao3 authored Jan 23, 2026
```
1,not find nvte_dgelu
2,fsdp_group is not none
3,CPUOffloadEnabled change to cpp_offload_v1
Signed-off-by: maxiao3 <maxiao3@sugon.com>

See merge request dcutoolkit/deeplearing/TransformerEngine!74
```
  284d3f6f
- Merge branch 'develop_v2.10' into release_v2.10 · bd05b0dc
  wenjh authored Jan 23, 2026
  
  bd05b0dc
- Fix issues related to L0cpp tests · 8fc9d8f1
  maxiao3 authored Jan 23, 2026
```
1,Resolve out-of-bounds issues for types struct
2,Fix TestFusedCastFloat8Vectorwise test case failure
Signed-off-by: maxiao3 <maxiao3@sugon.com>

See merge request dcutoolkit/deeplearing/TransformerEngine!73
```
  8fc9d8f1
- Merge branch 'develop_v2.10' into release_v2.10 · 7aeb5a72
  wenjh authored Jan 23, 2026
  
  7aeb5a72
- [DCU] Remove redundant shared memory in rowwise kernel · 261e476b
  zc20020701 authored Jan 23, 2026
```
Signed-off-by: zhaochao <zhaochao1@sugon.com>

See merge request dcutoolkit/deeplearing/TransformerEngine!72
Co-authored-by: zhaochao <zhaochao1@sugon.com>
```
  261e476b
- Merge branch 'develop_v2.10' into release_v2.10 · d786eedd
  wenjh authored Jan 23, 2026
  
  d786eedd
- Refine the constraints while using lightop in gemm.py · 6c9dc19d
  wenjh authored Jan 23, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  6c9dc19d
21 Jan, 2026 3 commits
- Merge branch 'develop_v2.10' into release_v2.10 · e2cc2fc4
  wenjh authored Jan 21, 2026
  
  e2cc2fc4
- Add NVTE_USE_LIGHTOP env var to control lightop import · 59b49b47
  maxiao3 authored Jan 21, 2026
```
Signed-off-by: maxiao3 <maxiao3@sugon.com>

See merge request dcutoolkit/deeplearing/TransformerEngine!71
```
  59b49b47
- Merge develop_v2.10 · 96a104d5
  wenjh authored Jan 21, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  96a104d5
12 Jan, 2026 1 commit
- Fix building on nmz · 0fce42f7
  wenjh authored Jan 12, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  0fce42f7
09 Jan, 2026 3 commits
- Develop v2.10 · 13123839
  dongchl authored Jan 09, 2026
```
rollback activation offloading implementation

See merge request dcutoolkit/deeplearing/TransformerEngine!70
Co-authored-by: dongcl <791582849@qq.com>
```
  13123839
- Merge branch 'develop_v2.10' into release_v2.10 · abec28e8
  wenjh authored Jan 09, 2026
  
  abec28e8
- Fix swizzle, swap_first_dims and RMSNorm issues · e6f2caf5
  wenjh authored Jan 09, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  e6f2caf5
08 Jan, 2026 2 commits
- Merge branch 'develop_v2.10' into release_v2.10 · 8f468f42
  wenjh authored Jan 08, 2026
  
  8f468f42
- Fix tests of L0 test_numeric and L1 test_fusible_ops · 953b6d68
  wenjh authored Jan 08, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>

See merge request dcutoolkit/deeplearing/TransformerEngine!67
```
  953b6d68
07 Jan, 2026 4 commits
- Merge branch 'develop_v2.10' into release_v2.10 · e8c89225
  wenjh authored Jan 07, 2026
  
  e8c89225
- Add nmz support · dc86f372
  wenjh authored Jan 07, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  dc86f372
- Merge branch 'develop_v2.10' into release_v2.10 · 72295c6e
  wenjh authored Jan 07, 2026
  
  72295c6e
- Rename package for tefl · 08be824c
  wenjh authored Jan 07, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  08be824c
06 Jan, 2026 1 commit
- Merge branch 'develop_v2.10' into release_v2.10 · 3d5f8cb7
  wenjh authored Jan 06, 2026
  
  3d5f8cb7
05 Jan, 2026 3 commits
- Rename tefl hygon backend · bdf3d931
  wenjh authored Jan 05, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  bdf3d931
- Make hygon backend installable · 40816696
  wenjh authored Jan 05, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  40816696
- Add hygon backend for TE-FL · 73d959a4
  wenjh authored Jan 05, 2026
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  73d959a4
31 Dec, 2025 7 commits
- Merge branch 'develop_v2.10' into release_v2.10 · ad5fbfb5
  wenjh authored Dec 31, 2025
  
  ad5fbfb5
- Using pip install to build · b0871127
  wenjh authored Dec 31, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  b0871127
- Merge branch 'develop_v2.10' into release_v2.10 · 85ea3dd2
  wenjh authored Dec 31, 2025
  
  85ea3dd2
- Add bias fwd/bwd at group gemm · cb2fe806
  wenjh authored Dec 31, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  cb2fe806
- Merge branch 'develop_v2.10' into release_v2.10 · aaab9f18
  wenjh authored Dec 31, 2025
  
  aaab9f18
- Fix new gemm · f796eb80
  wenjh authored Dec 31, 2025
```
Signed-off-by: wenjh <wenjh@sugon.com>
```
  f796eb80
- Merge branch 'develop_v2.10' into release_v2.10 · 69326735
  wenjh authored Dec 31, 2025
  
  69326735