ColossalAI/extensions/pybind
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>
2024-08-16 13:56:38 +08:00
..
cpu_adam [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00
flash_attention [Feature] Zigzag Ring attention (#5905) 2024-08-16 13:56:38 +08:00
inference add paged-attetionv2: support seq length split across thread block (#5707) 2024-05-14 12:46:54 +08:00
layernorm [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00
moe [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00
optimizer [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00
softmax [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00
__init__.py [Inference/Refactor] Refactor compilation mechanism and unified multi hw (#5613) 2024-04-24 14:17:54 +08:00