Making large AI models cheaper, faster and more accessible
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Edenzzzz
f5c84af0b0
[Feature] Zigzag Ring attention (#5905)
* halfway
* fix cross-PP-stage position id length diff bug
* fix typo
* fix typo
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* unified cross entropy func for all shardformer models
* remove redundant lines
* add basic ring attn; debug cross entropy
* fwd bwd logic complete
* fwd bwd logic complete; add experimental triton rescale
* precision tests passed
* precision tests passed
* fix typos and remove misc files
* [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
* add sp_mode to benchmark; fix varlen interface
* update softmax_lse shape by new interface
* change tester name
* remove buffer clone; support packed seq layout
* add varlen tests
* fix typo
* all tests passed
* add dkv_group; fix mask
* remove debug statements
---------
Co-authored-by: Edenzzzz <wtan45@wisc.edu>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
|
3 months ago |
| .. |
|
__init__.py
|
…
|
|
|
flash_attention_dao_cuda.py
|
[Feature] Zigzag Ring attention (#5905)
|
3 months ago |
|
flash_attention_npu.py
|
…
|
|
|
flash_attention_sdpa_cuda.py
|
…
|
|
