- 21 Aug, 2024 2 commits
-
-
Charlene Yang authored
* add support for padding in UnfusedDPA Signed-off-by:
Charlene Yang <8636796+cyanguwa@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add support for padding_causal/_bottom_right Signed-off-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
Xiaowei Ren authored
* add window_size to AttnFuncWithCP Signed-off-by:
Xiaowei Ren <xren@nvidia.com> * add seq_offsets_qkvo for cudnn thd Signed-off-by:
Xiaowei Ren <xren@cs-cw-dfw-login-01.cm.cluster>
-
- 20 Aug, 2024 1 commit
-
-
hXl3s authored
feat(pytorch): Allow TransformerLayer and MultiheadAttention to accept sequence length parameters (#1066) * Added ability for seqlen for transformer and mha layer Signed-off-by:
Lukasz Pierscieniewski <lukaszp@nvidia.com> * Documentation for new parameters Signed-off-by:
Przemek Tredak <ptredak@nvidia.com> --------- Signed-off-by:
Kirthi Shankar Sivamani <ksivamani@nvidia.com> Co-authored-by:
-
- 16 Aug, 2024 2 commits
-
-
Shijie authored
* support dtype casting fusion in FusedAdam Signed-off-by:
Shijie Wang <jaywan@nvidia.com> * minor changes Signed-off-by:
Tim Moon <tmoon@nvidia.com> * Copy CUDA headers for framework sdists Signed-off-by:
-
Xiaowei Ren authored
* add window_size to AttnFuncWithCP Signed-off-by:
-
- 13 Aug, 2024 2 commits
-
-
Charlene Yang authored
* update example/benchmark scripts Signed-off-by:
-
Charlene Yang authored
* merge k_channels and v_channels back to kv_channels and accept a tuple Signed-off-by:
-
- 10 Aug, 2024 1 commit
-
-
Tim Moon authored
* Add op for in-place add Signed-off-by:
Tim Moon <4406448+timmoon10@users.noreply.github.com> --------- Signed-off-by:
-
- 09 Aug, 2024 2 commits
-
-
Xin Yao authored
* use fused_multi_cast_transpose Signed-off-by:
Xin Yao <xiny@nvidia.com> * fix input being empty tensor Signed-off-by:
-
Alp Dener authored
[C/PyTorch] Fixed incorrect use of `torch.distributed.new_group()` when creating intra-node group in `initialize_ub()` (#1087) * updated initialize_ub() to use new_subgroups_by_enumeration() to generate intra-node groups, added new unit tests for TE layers with comm overlap Signed-off-by:
Alp Dener <adener@nvidia.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by:
-
- 06 Aug, 2024 1 commit
-
-
Charlene Yang authored
* add multi-latent attention for DPA Signed-off-by:
-
- 01 Aug, 2024 2 commits
-
-
Xiaowei Ren authored
* use 2hd layout Signed-off-by:
-
Xin Yao authored
* fix workspaces and unfused bias in multi-stream cuBLAS * Expose num_streams via pybind * Fix C-compatibility * rm importing packaging in test_fused_attn.py --------- Signed-off-by:
Phuong Nguyen <phuonguyen@nvidia.com>
-
- 31 Jul, 2024 1 commit
-
-
Przemyslaw Tredak authored
* Ensure that the inputs to custom calls are contiguous Signed-off-by:
-
- 30 Jul, 2024 1 commit
-
-
Kirthi Shankar Sivamani authored
Rm unused import causing CI failures Signed-off-by:
-
- 23 Jul, 2024 1 commit
-
-
Alp Dener authored
[PyTorch] Fixing hang in `initialize_ub()` for multi-node runs after PR901 removal of MPI-dependence (#986) * Re-implementing PR901 (removing MPI-dependence in Userbuffers) with multi-node fixes * passing data-parallel rank/size info from torch.distributed to userbuffers Signed-off-by:
-
- 17 Jul, 2024 1 commit
-
-
Tim Moon authored
* Add option to pass kwargs to CUDA graph module Signed-off-by:
-
- 10 Jul, 2024 1 commit
-
-
Charlene Yang authored
* add cuDNN swa Signed-off-by:
-
- 09 Jul, 2024 1 commit
-
-
Tim Moon authored
* Add basic infrastructure for Sequential module Signed-off-by:
-
- 03 Jul, 2024 1 commit
-
-
Charlene Yang authored
* update to FE 1.5.1 and add bottom right causal Signed-off-by:
-
- 01 Jul, 2024 1 commit
-
-
Charlene Yang authored
* update FE to 1.5.2 Signed-off-by:
-
- 26 Jun, 2024 2 commits
-
-
Charlene Yang authored
* disable CP-THD tests for fused attn on <sm90 Signed-off-by:
-
Tim Moon authored
cache was added in Python 3.9. Signed-off-by:
-
- 25 Jun, 2024 1 commit
-
-
Xin Yao authored
* GroupedGEMM via multi-stream cublas * fix A/B is nullptr while D is not nullptr * add fp8 grouped gemm * register with TorchScript * add the GroupedLinear layer --------- Signed-off-by:
Jiang Shao <jiangs@nvidia.com> Co-authored-by:
Qi Zhang <qizhang@nvidia.com> Co-authored-by:
-
- 18 Jun, 2024 1 commit
-
-
Charlene Yang authored
* simplify offset tensors Signed-off-by:
-
- 15 Jun, 2024 1 commit
-
-
Charlene Yang authored
* subclass DPA with BaseModule and test with test_gpt_checkpointing Signed-off-by:
-
- 14 Jun, 2024 2 commits
-
-
Kirthi Shankar Sivamani authored
* Apply formatting Signed-off-by:
-
Charlene Yang authored
* add attention docs Signed-off-by:
-
- 12 Jun, 2024 1 commit
-
-
rybakov authored
Signed-off-by:
Oleg Rybakov <orybakov@nvidia.com> Co-authored-by:
-
- 10 Jun, 2024 1 commit
-
-
Xiaowei Ren authored
* add seq_offsets_qkvo for cudnn thd Signed-off-by:
-
- 07 Jun, 2024 1 commit
-
-
Kirthi Shankar Sivamani authored
* Remove interval arg from recipe Signed-off-by:
-
- 06 Jun, 2024 1 commit
-
-
Kirthi Shankar Sivamani authored
Cleanup Signed-off-by:
-
- 03 Jun, 2024 1 commit
-
-
Tim Moon authored
* Modify CUDA graph tests to use grad accumulation steps Signed-off-by:
-
- 30 May, 2024 3 commits
-
-
Charlene Yang authored
* add THD support Signed-off-by:
-
Xin Yao authored
* add multi-tensor kernels Signed-off-by:
-
Tim Moon authored
* Initial refactor of FP8 workspaces in Linear module Signed-off-by:
-
- 25 May, 2024 1 commit
-
-
Paweł Gadziński authored
* Fixed Llama tutorial. Changed batch size and added fused=True. Signed-off-by:
Pawel Gadzinski <pgadzinski@nvidia.com> Signed-off-by:
root <root@ipp2-0037.nvidia.com> * Tutorial updated but not complete yet. Signed-off-by:
root <root@ipp2-1661.nvidia.com> * Comments Signed-off-by:
root <root@ipp2-2373.nvidia.com> Co-authored-by:
root <root@ipp2-1588.nvidia.com> Co-authored-by:
root <root@ipp2-2371.nvidia.com> Co-authored-by:
root <root@ipp2-1589.nvidia.com> Co-authored-by:
Sudhakar Singh <sudhakars@nvidia.com> Co-authored-by:
-
- 22 May, 2024 1 commit
-
-
Phuong Nguyen authored
* added alignment requirements for CuBLAS heuristics Signed-off-by:
-
- 20 May, 2024 1 commit
-
-
Paweł Gadziński authored
* Calibration fix Signed-off-by:
-
- 17 May, 2024 1 commit
-
-
Charlene Yang authored
* fix inconsistency for attn mask; now True means participating in attn Signed-off-by:
-
