GitLab

This bug will cause bug [ERROR] failed (exitcode: -11) local_rank: 0 (pid: 1761020) of binary: ~/megatron/bin/python.

That is because we miss the rng_states that is required in attention recompute (for dropout), but no hint is provided.  

It is very very very difficult to trace and cost me two weeks.

```python
before the start of training step] datetime: 2024-07-22 18:26:45 
[2024-07-22 18:27:00,941] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: -11) local_rank: 0 (pid: 1761020) of binary: /home//miniconda3/envs/megatron/bin/python
Traceback (most recent call last):
  File "/home//miniconda3/envs/megatron/bin/torchrun", line 33, in <module>
    sys.exit(load_entry_point('torch==2.2.1+cu121', 'console_scripts', 'torchrun')())
  File "/home//miniconda3/envs/megatron/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
    return f(*args, **kwargs)
  File "/home//miniconda3/envs/megatron/lib/python3.10/site-packages/torch/distributed/run.py", line 812, in main
    run(args)
  File "/home//miniconda3/envs/megatron/lib/python3.10/site-packages/torch/distributed/run.py", line 803, in run
    elastic_launch(
  File "/home//miniconda3/envs/megatron/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 135, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/home//miniconda3/envs/megatron/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 268, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
```
Signed-off-by: 李金梁 <975761915@qq.com>

* initialize output tensors to 0 for THD while waiting for cuDNN bug fix
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



* move fill_() to F16 loop
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix fused_attn_bwd()
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* correct typo in check_set_window_size
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* use nvtx3 instead
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* add cuDNN swa
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix SWA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add set_deterministic and minor fixes for swa
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add AttentionParams
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* change window_size to int64_t; fix swa/determinism tests; cache _attention_backends
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add window_size to get_backend; fix jax and paddle
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes; add set_deter to bwd_impl
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix unit tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix FP8 tests due to determinism
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add support matrix for SWA and bias
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



* minor fixes and lint
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



* minor fixes
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add wording on window_size special cases
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweak on wording
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix jax assertion error
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix wording
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* call bwd with deterministic=true for jax/paddle
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add determinism words in documentation
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* update to FE 1.5.1 and add bottom right causal
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



* adjust logic for backend selection
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



* update FE to 1.5.2
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add get_attention_backend function
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



* update get_attention_backend
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix get_attention_backend
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



* tweak get_attention_backend and fix unit tests
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



* minor fixes for unfused, get_backend, etc
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



* Update transformer_engine/pytorch/attention.py
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix cpu offload
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes for get_attention_backend
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* explicitly skip FP32 and padding tests because there is no support
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fix for window size check
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update check_set_window_size and add enc_dec_attn_mask_type/enc_dec_window_size
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



* minor fixes
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



---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

* update FE to 1.5.2
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* enable unfused attn for cross attn
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* unify logging info
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* omit cudnn 9.1.1 and 9.2.1 due to bugs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* set cu_seqlens_padded to cu_seqlens by default
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace variable name with ctx.variable
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* Revert "enable unfused attn for cross attn"

This reverts commit bc49f14fca904217a711b4a86c45a4a739a17a14.
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* restrict cudnn version for fp8 tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove mha_fill for FP8
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* Revert "remove mha_fill for FP8"

This reverts commit 83ffc44114dc6eb3d426d742b6c5a4d34805ec04.
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* lower cudnn version to >=9.2.1
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



---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* simplify offset tensors
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes; tests pass
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix C lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace with_offset with with_padding
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace with_padding with padded
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



* minor fixes after merge
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



* minor fix for fused attn fwd/bwd calls
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



* fix Jax
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



* adjust spacing in docstring
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix pytorch tests; fix paddle api
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



* fix lint
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



* fix attn_biases
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix AttnFuncWithCP backward
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix jax
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



* fix attn with CP
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix paddle
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



---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

fix tp_initialized error
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* subclass DPA with BaseModule and test with test_gpt_checkpointing
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* test DPA only
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* test save and load
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove debug info
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweaks
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweak
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add hook in case core_attention._extra_state is missing
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* check named buffers in BaseModule; remove FP8 scratchpad override function; test FP8 for sm90+
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



* minor fixes: test size, interval in recipe, named_buffer loop
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* move BaseModule from FusedAttention to DPA
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



---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Apply formatting
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Apply formatting
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Initial config test
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* remove linters, fix clang-format
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix clang-format
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix clang-format
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Remove lint
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Adjust config
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* use config file
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* adjust pylintrc
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* pre-format fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Python only
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Add FA module
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Update CI configs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* CRLF -> LF
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* format
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* revert accidental formatting changes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* try with sudo
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* cpp formatting
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix pylint error properly
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* some review comments
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* lint fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* add fp8 attn include in the correct file
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* autofix PRs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* add attention docs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attention doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attention doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attention doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attn doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attn doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attn doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: update attention doc
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* first draft
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweak to first draft
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up pictures
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* first draft for review
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add logging info/debug
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fix of an SWA message
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* use subprocess instaed of os.sys
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up benchmark script
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add example script and update notebook
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweak
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor tweaks
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix Jax/Paddle related comments
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* rerun H100 benchmark
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* restrict fp8 tests to sm90+
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* move get_cudnn_version from common to pytorch utils
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* Add norm_factor arg into DotProductAttention
Signed-off-by: Boxiang Wang <boxiangw@nvidia.com>

* Change kwarg name from `norm_factor` to `softmax_scale`
Signed-off-by: Boxiang Wang <boxiangw@nvidia.com>

* Change all norm_factor representation into softmax_scale
Signed-off-by: Boxiang Wang <boxiangw@nvidia.com>

* Update transformer_engine/pytorch/attention.py
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

* Update attention.py changing typo
Signed-off-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>

---------
Signed-off-by: Boxiang Wang <boxiangw@nvidia.com>
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

* add seq_offsets_qkvo for cudnn thd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* add seq_offsets_qkvo to AttnFuncWithCP
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix seq_offsets calculation of cudnn thd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* remove a thd assert
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix bias for thd test
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* add thd test for cudnn FA with CP
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* skip GQA/MQA test for cuDNN THD
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* make sure seq_offsets are computed with qkv_group of hd_hd_hd while CP>1
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix seq_offsets inputs
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* remove two comments
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix attn mask type for cudnn thd with cp
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix attn_mask_type check
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix attn_mask_type for cudnn fa with thd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix a typo
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix out dout in bwd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* assert cudnn+thd does not support attn bias
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* check if attn_mask_type has padding
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* minor change
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* change cp test batch size to 2
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix code format
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix two assert info
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix assert comment
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix assert comments
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* minor fix
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix assert comments
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

---------
Signed-off-by: Xiaowei Ren <xren@nvidia.com>
Co-authored-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

Cleanup
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* add THD support
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add seq_offsets_o and use new offset calculation
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* addition to previous commit; fix unit test
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add None for offset_o gradient
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: test padding between sequences
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: fix tests for padding between sequences
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix tests for sbhd/bshd layouts; clean up
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update cudnn-frontend and add tests for max_seqlen_q=1 and d=256 for inference
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* test sbhd/bshd layouts for sq1, d256 inference case
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace wording from accumulative to cumulative
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add offset tensors to custom fp8 mha tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add version control for cuDNN
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add sm>=90 constraint for thd support
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix cuDNN support for sq=1, d=256
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint and minor tweak for fp8 tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* modify cudnn version and restrict MQA/GQA support for THD
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add notes for seq offset tensors
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add dummy tensor to pass jax build
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add dummy tensor to pass paddle build
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix Jax CI
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

Make sure RoPE frequencies are in FP32
Signed-off-by: Tim Moon <tmoon@nvidia.com>

* 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: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* Tutorial notebook reseted - removed fuse=true
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* Removed fused=true
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* Batch size back to 8
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* Typo and commented out line
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* fixed whitespace
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* fixed whitespace
Signed-off-by: root <root@ipp2-0037.nvidia.com>

* Added comment to attention line. Fixed potential bug with loading weights - now loading works correctly, confirmed by the generation code.
Signed-off-by: root <root@ipp2-1661.nvidia.com>

* Comments
Signed-off-by: root <root@ipp2-1661.nvidia.com>

* Models cast added again
Signed-off-by: root <root@ipp2-1661.nvidia.com>

* Weight download info
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Moved parameter gate_proj_size to config
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* gate_proj_size removed and put immediate_size instead
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Llama 3 added to tutorial
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Typos fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Typos fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Fixed model loading
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Loading fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Different dim for attention
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Reversed other commit
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Changed name to kv_channels
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Fixed typo
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Back to kv_channels in transformer layer
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Back to kv_channels in transformer layer
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Small bug fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Small bug fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Test fix
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* changed file modes
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* lint fix and resolved conflict
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* lint fix and resolved conflict
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

* Lint fix, hopefully last
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>

---------
Signed-off-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Signed-off-by: root <root@ipp2-0037.nvidia.com>
Signed-off-by: root <root@ipp2-1661.nvidia.com>
Co-authored-by: root <root@ipp2-2373.nvidia.com>
Co-authored-by: root <root@ipp2-1588.nvidia.com>
Co-authored-by: Pawel Gadzinski <pgadzinski@nvidia.com>
Co-authored-by: root <root@ipp2-0037.nvidia.com>
Co-authored-by: root <root@ipp2-1661.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: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

replaced deprecated pkg_resources with packaging
Signed-off-by: Alp Dener <adener@nvidia.com>

* fix inconsistency for attn mask; now True means participating in attn
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix sliding window window_size for decoder+padding combination
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* revert paddle changes regarding mask
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* revert softmax to 1-mask;0-keep
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* enforce 1-mask out; 0-keep rule for jax masks
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix jax lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* revert pytorch mask changes; some kept in tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* revert to jax fused attn on main
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* inverse mask logic for get_cu_seqlens/_and_indices in PyTorch implementation and mask generation in unit tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* temporarily disable update_weight_scale_inv
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* enforce window_size for decoder
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add docstring for mask definition 1-mask out;0-keep
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add aux_ctx_tensors to save_for_backward
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* tweak make_decoder_mask and make_mask in jax tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* skip dBias for shapes other than 1HSS; otherwise dq/dk/dv NaNs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* expand attn_biases from list to variables in save_for_backward
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix use of variable before assignment in jax dact_lu
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove window size definition for decoder
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add change notes in README for padding mask in PyTorch
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* tweak padding mask notes in README
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* expand list to tensors for save_for_backwards
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

Signed-off-by: kunlunl <kunlunl@nvidia.com>
Co-authored-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

Bump FA version to 2.5.8
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* initialize tp_group for FP8 DPA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix cuDNN version in unit tests for cuDNN v9
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add hook to ignore missing fused_attn._extra_states if training from old checkpoints
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove test and redundant implementation from last commit
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove warning message and replace with docstring
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove tp_size/tp_group in FusedAttention; amax reduction is handled with fp8_group
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* move core_attention.fused_attention._extra_state to core_attention._extra_state
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* simplify post_state_dict_hooks between FU and DPA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add temporary test
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove previous attempts to move core_attention.fused_attention to core_attention; keep the test
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove the test
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* disable pylint self arg for hook which is required by hook
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

* Fix linter warnings from unused args
Signed-off-by: Tim Moon <tmoon@nvidia.com>

* Update .gitignore
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

---------
Signed-off-by: Tim Moon <tmoon@nvidia.com>
Signed-off-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

remove tp_size/tp_group as amax reduction is handled by fp8_group()
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* make FusedAttn with CP support bias
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* assert Alibi cannot work with CP
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* syntax fix
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix variable name
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix tensor shapes
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* a typo fix
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix bias indexing for CP
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* bug fix
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* add attn bias tests
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* change dbias update location
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix CP test model configs
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* change CP test sequence length
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* make AttnFuncWithCP support qkv format of sbhd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* make sure qkv are contiguous for CP in cuDNN fused attn
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* change assert message
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix code format
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

---------
Signed-off-by: Xiaowei Ren <xren@nvidia.com>
Co-authored-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

* Try using global buffer for cu_seqlens
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Avoid using functools.lru_cache
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Vasudevan Rengasamy <vrengasamy@nvidia.com>

* WIP: fp8 v1 fprop integration
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: minor fixes
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add debug info
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add more debug info
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fprop working for h1; w/ debug info
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: add bprop
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* cleanup; bprop running but has mismatches
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add gitlab frontend as submodule
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up and add back v0.9.2 FE support; fprop/bprop passing with 5e-2 tols
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix after merge; add bias_b/h to caching descriptor
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* distinguish fwd/bwd tensor types for bprop
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fix for F16 cases; include added dqkv_type and d_scale_dp
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* adjust out shape for bwd in test
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add casting from/to FP8 to DPA module
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: bshd_bshd_bshd layout
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* WIP: support all sbhd/bshd layouts
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add qkvpacked and kvpacked support in both FusedAttnFunc and C levels
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove qkvpacked/kvpacked calls in DPA module (used for testing)
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove tp setup; add allow_non_contiguous; update FE; revert to sbh3d in tests; clean up
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add NVTE_FP8_DPA_BWD to control whether to use FP8 bwd or F16 bwd
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix MQA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix MQA/GQA in FP8 v1 API
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update FE to 705d8e3, with API change
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* test causal mask
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* restrict mha_fill for THD format
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix fused attn with CP and comment out is_alibi code
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up FE0.9 vs FE1.0 FP8 implementations, and related unit tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* change NVTE_FP8_DPA_BWD default to 1, and fix its use in qkvpacked/kvpacked APIs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint and self.tp_size/group in FusedAttention()
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update FE to 6902c94
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add FP8 MHA support
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update to FE v1.3.0
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes for FP8 MHA with different configs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* emit stats regardless of is_training
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix linear when input is not Float8Tensor
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix d_out type when f16 bprop
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix user buffer for layernorm_linear/linear and revert two FP8 casts in MHA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add docstring for fp8_dpa/mha in recipe
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* fix backend selection to avoid FA
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace transpose with transpose_2d
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* use RMSE for FP8 unit tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace two more transpose with transpose_2d
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add FP8 initialization to FusedAttention
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* rm docs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Revert "add FP8 initialization to FusedAttention"

This reverts commit 15fffd825d6f23f31ea709b16ba01dfd61efabf8.
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Change order of ctxs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* minor fixes
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add back docs and mark as beta
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* minor fixes for tests and docs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* FP8 cuda graphs
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Vasudevan Rengasamy <vrengasamy@nvidia.com>
Co-authored-by: Charlene Yang <charleney@nvidia.com>

* Fix numerics
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* exclude torch compile from numerics tests
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* More numerics fixes
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fix tests
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Fix CI
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* rm fusion from unfused path
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Vasudevan Rengasamy <vrengasamy@nvidia.com>
Co-authored-by: Charlene Yang <charleney@nvidia.com>

* Enable DGRAD RS overlap
Signed-off-by: Jaemin Choi <jaeminc@nvidia.com>

* fix lint; apply suggestions
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Jaemin Choi <jaeminc@nvidia.com>
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Vasudevan Rengasamy <vrengasamy@nvidia.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

This reverts commit 965803c9.

* TP-RS overlap with send/recv

Atomic GEMM based TP-RS overlap with send/recv
Signed-off-by: Sangkug Lym <slym@nvidia.com>

Specify userbuffer overlap method of each overlap instance
Signed-off-by: Sangkug Lym <slym@nvidia.com>

P2P TP-RS overlap with fp8 GEMM outputs
Signed-off-by: Sangkug Lym <slym@nvidia.com>

Fix TP-RS overlap with send/recv
Signed-off-by: Sangkug Lym <slym@nvidia.com>

* cleanup
Signed-off-by: Sangkug Lym <slym@nvidia.com>

* cleanup
Signed-off-by: Sangkug Lym <slym@nvidia.com>

* linting
Signed-off-by: Sangkug Lym <slym@nvidia.com>

* fix typo
Signed-off-by: Sangkug Lym <slym@nvidia.com>

---------
Signed-off-by: Sangkug Lym <slym@nvidia.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

[Pytorch] Update context parallel softmax lse correction func.
Signed-off-by: kitefang <kitefang@tencent.com>
Co-authored-by: kitefang <kitefang@tencent.com>

Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Modified MHA and DPA logic to use causal softmax and FA for inference
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Adjusted unfused attention and softmax logic for inference
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Cleaned up the code per pylint
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Added test cases to evaluate numerics of incremental decoding
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Apply suggestions from code review
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: Oleg Goncharov <64355998+Oleg-Goncharov@users.noreply.github.com>

* Apply suggestions from code review [sequence start-end]
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: Oleg Goncharov <64355998+Oleg-Goncharov@users.noreply.github.com>

* Apply suggestions from code review [inference_params offset update]]
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: Oleg Goncharov <64355998+Oleg-Goncharov@users.noreply.github.com>

* Fixed bug in KV-cache indices and updated test suite
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Added inference_params description and applied suggestions from the code review
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Adjusted absolute tolerances in numerics tests
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

* Cleaned up the files per pylint
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>

---------
Signed-off-by: Oleg Goncharov <ogoncharov@nvidia.com>
Signed-off-by: Oleg Goncharov <64355998+Oleg-Goncharov@users.noreply.github.com>
Co-authored-by: Przemyslaw Tredak <ptredak@nvidia.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* added support for arbitrary bias shapes for fused_attn
Signed-off-by: Alp Dener <adener@nvidia.com>

* Fix linting
Signed-off-by: Alp Dener <adener@nvidia.com>

* Add b1ss/bhss/11ss bias shapes when not requiring dBias
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add bias_b/h to plan cache
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fixed compile errors after PR653 merge
Signed-off-by: Alp Dener <adener@nvidia.com>

* updated JAX unittests for new bias shapes
Signed-off-by: Alp Dener <adener@nvidia.com>

* fixed mismatched mask type checking
Signed-off-by: Alp Dener <adener@nvidia.com>

* corrected skip condition
Signed-off-by: Alp Dener <adener@nvidia.com>

* fix selection logic for A100s
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* corrected skip checks for bias shapes
Signed-off-by: Alp Dener <adener@nvidia.com>

* resolved test issues but neginf with float16 is still problematic with JAX
Signed-off-by: Alp Dener <adener@nvidia.com>

* new bias shapes passing TE JAX CI for seqlen <= 512, seq_q == seq_kv and h_q == h_kv conditions
Signed-off-by: Alp Dener <adener@nvidia.com>

* TE/JAX fused attn tests for new bias shapes passing with neg_inf=-2**27 for Bfloat16 and -2**15 for Float16
Signed-off-by: Alp Dener <adener@nvidia.com>

* code style fixes and test parameter ID cleanup
Signed-off-by: Alp Dener <adener@nvidia.com>

* fixed incorrect skip condition for backward fused attn test
Signed-off-by: Alp Dener <adener@nvidia.com>

---------
Signed-off-by: Alp Dener <adener@nvidia.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: Alp Dener <adener@nvidia.com>

* added non-reentrant mode support to TE checkpoint
Signed-off-by: Alp Dener <adener@nvidia.com>

* updated get_cuda_rng_tracker kwarg to get_rng_state_tracker to remain consistent with other TE API
Signed-off-by: Alp Dener <adener@nvidia.com>

* docstring cleanup
Signed-off-by: Alp Dener <adener@nvidia.com>

* added mechanism to disable bias_gelu_nvfusion in LayerNormMLP when checkpointing in non-reentrant mode
Signed-off-by: Alp Dener <adener@nvidia.com>

* refactored checkpoint and recompute hook names to match PyTorch implementation
Signed-off-by: Alp Dener <adener@nvidia.com>

* Fixed incorrect reference before assignment
Signed-off-by: Alp Dener <adener@nvidia.com>

* fixed argument error in calling native PyTorch checkpoint
Signed-off-by: Alp Dener <adener@nvidia.com>

* fixed linting errors for missing docstrings
Signed-off-by: Alp Dener <adener@nvidia.com>

* Fix lint
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* bias GELU fusion consistency between checkpoint test and reference comparison
Signed-off-by: Alp Dener <adener@nvidia.com>

---------
Signed-off-by: Alp Dener <adener@nvidia.com>
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Use fused implementation of RoPE in MultiHeadAttention
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>

* Fix freqs dtype
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* test alibi between fa and fu
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* move alibi slopes and bias to global to avoid repeating calculation
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix alibi slopes/bias generation
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix _is_flash_attention_supported to allow alibi type
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* disable padding mask when alibi is used for fused attn arbi backend
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* add support for custom [n_heads] alibi_slopes in flash, fused, unfused attention
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up last commit
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove alibi_type=none tests as they are unnecessary
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update cudnn-frontend to 1.0.2
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* change bias/dbias shape to allow b,1/1,h/b,h in arbi backend
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* tweak tests for arbi post_scale_bias [1,h,s,s] or alibi_slopes [n_heads]
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* change bias/dbias shape in max512 backend - incomplete
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove max512 changes from last commit and disable max512 (and arbi temporarily) for [b, h, s, s]; pending cuDNN backend support
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* clean up and tweak backend selection logic
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* replace || with () in docstring
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix bias shape for max512 backend
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* combine slopes/bias generation to one function get_alibi() and fix alibi tests
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix lint
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* fix PR557 bugs
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* Update transformer_engine/pytorch/attention.py
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

* encapsulate global alibi tensors into a dict cache
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* reduce alibi slopes test size
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* update to cudnn-frontend 1.0.3
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* use dBias shape to define bias_b/bias_h because jax materializes dBias rather than Bias in bwd abstract
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>

Do not cache sequence lengths based on layer number
Signed-off-by: Tim Moon <tmoon@nvidia.com>
Co-authored-by: Kirthi Shankar Sivamani <ksivamani@nvidia.com>

* Update cudnn frontend to 1.0.3 to fix cudnn v9 Nans
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* make d_out contiguous for bwd
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* remove cudnnDestroy to let torch handle it
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>

* Update transformer_engine/pytorch/attention.py
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

* Update transformer_engine/pytorch/attention.py
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

* Update transformer_engine/pytorch/attention.py
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>

---------
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Signed-off-by: cyanguwa <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: Tim Moon <4406448+timmoon10@users.noreply.github.com>