[pull] main from NVIDIA:main #17
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
![pull[bot]](https://avatars.githubusercontent.com/in/12910?s=60&v=4){kind=small}
#957) * NVTE_OVERRIDE_MAX_SEQ_LEN Signed-off-by: Frank Lin <[email protected]> * small fix Signed-off-by: Frank Lin <[email protected]> * preserve old amax_and_scale_update_inplace and new amax_and_scale_update_inplace Signed-off-by: Frank Lin <[email protected]> * remove useless code path; try to simplify logic within the baseline Signed-off-by: Frank Lin <[email protected]> * simplify logic Signed-off-by: Frank Lin <[email protected]> * small fix Signed-off-by: Frank Lin <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix comments from Timmoon Signed-off-by: Frank Lin <[email protected]> * fix comments from Timmoon Signed-off-by: Frank Lin <[email protected]> * Update transformer_engine/paddle/distributed.py Co-authored-by: Tim Moon <[email protected]> Signed-off-by: Frank Lin <[email protected]> * diable bw fp8 update Signed-off-by: Frank Lin <[email protected]> * fix lint Signed-off-by: Frank Lin <[email protected]> * fix ci error Signed-off-by: Frank Lin <[email protected]> --------- Signed-off-by: Frank Lin <[email protected]> Co-authored-by: Frank Lin (Engrg-Hardware 1) <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Tim Moon <[email protected]>
Fix typo when selecting tuned RMSNorm kernels Signed-off-by: Tim Moon <[email protected]>
* Integrate experimental ragged offset Signed-off-by: Reese Wang <[email protected]> * Use per sequence based offsets Signed-off-by: Reese Wang <[email protected]> * Format Signed-off-by: Reese Wang <[email protected]> * Remove v/o_seq_offsets Signed-off-by: Reese Wang <[email protected]> * Add FP16 sanity tests and remove forward tests from the automatically run tests Signed-off-by: Reese Wang <[email protected]> * Enhance input checks Signed-off-by: Reese Wang <[email protected]> * Separate fused attn to 2 differnt APIs and add the docs Signed-off-by: Reese Wang <[email protected]> * Add experimental to the docs Signed-off-by: Reese Wang <[email protected]> * Fix lint Signed-off-by: Reese Wang <[email protected]> * Add runtime segments check Signed-off-by: Reese Wang <[email protected]> * Remove finished TODO Signed-off-by: Reese Wang <[email protected]> --------- Signed-off-by: Reese Wang <[email protected]>
* removed libcuda.so link at compile time for TE/PyTorch extension Signed-off-by: Alp Dener <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * linting fixes Signed-off-by: Alp Dener <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * updated get_symbol() in TE/common/cuda_utils.h to new impl based on cudaGetDriverEntryPoint Signed-off-by: Alp Dener <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix duplicate quotation Signed-off-by: Alp Dener <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Alp Dener <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Kirthi Shankar Sivamani <[email protected]>
* update to FE 1.5.1 and add bottom right causal Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * adjust logic for backend selection Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update FE to 1.5.2 Signed-off-by: Charlene Yang <[email protected]> * add get_attention_backend function Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update get_attention_backend Signed-off-by: Charlene Yang <[email protected]> * fix get_attention_backend Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * tweak get_attention_backend and fix unit tests Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * minor fixes for unfused, get_backend, etc Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update transformer_engine/pytorch/attention.py Co-authored-by: Tim Moon <[email protected]> Signed-off-by: Charlene Yang <[email protected]> * fix cpu offload Signed-off-by: Charlene Yang <[email protected]> * minor fixes for get_attention_backend Signed-off-by: Charlene Yang <[email protected]> * explicitly skip FP32 and padding tests because there is no support Signed-off-by: Charlene Yang <[email protected]> * minor fix for window size check Signed-off-by: Charlene Yang <[email protected]> * update check_set_window_size and add enc_dec_attn_mask_type/enc_dec_window_size Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * minor fixes Signed-off-by: Charlene Yang <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Signed-off-by: Charlene Yang <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Tim Moon <[email protected]>
Fix size mismatch error in fp8 transpose. Signed-off-by: Dennis Liu <[email protected]>
) * remove implicit padding and unpadding Signed-off-by: Xin Yao <[email protected]> --------- Signed-off-by: Xin Yao <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Phuong Nguyen <[email protected]>
…olumn') to adapt DiT of PaddleMIX (#963) [Paddle] Fix forward and backward of Linear(parallel_mode='column') When te.Linear(parallel_mode='column') is not used in pairs with te.Linear(parallel_mode='row'), the output should to be all-gathered when forward and reduce-scattered when backward. Signed-off-by: minyu <[email protected]> Co-authored-by: Kirthi Shankar Sivamani <[email protected]>
* add parallel build without pyproject Signed-off-by: Phuong Nguyen <[email protected]> --------- Signed-off-by: Phuong Nguyen <[email protected]> Co-authored-by: Tim Moon <[email protected]>
Build for python < 3.8 Signed-off-by: Kirthi Shankar Sivamani <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot]
Can you help keep this open source service alive? 💖 Please sponsor : )