PR #26479 Add flash attention for `gpt_bigcode`

Add flash attention for `gpt_bigcode` #26479

amyeroberts merged 14 commits into huggingface:main from susnato:flash_attn_starcoder

added flash attention of gpt_bigcode

447703e7

younesbelkada approved these changes on 2023-09-29

younesbelkada requested a review from

ArthurZucker 2 years ago

changed docs

7baa248a

ArthurZucker commented on 2023-09-29

younesbelkada approved these changes on 2023-10-03

ArthurZucker approved these changes on 2023-10-03

Update src/transformers/models/gpt_bigcode/modeling_gpt_bigcode.py

bddd8e68

add FA-2 docs

7f38f86b

Merge branch 'flash_attn_starcoder' of https://github.com/susnato/tra…

50506faf

oops

28ddca39

younesbelkada requested a review from

ArthurZucker 2 years ago

younesbelkada requested a review from

ArthurZucker 2 years ago

ArthurZucker commented on 2023-10-08

Update docs/source/en/perf_infer_gpu_one.md Last Nit

542c2759

Ltrack approved these changes on 2023-10-14

Merge remote-tracking branch 'upstream/main' into HEAD

72b353bb

fix

f43ec5a4

oops

b2aa0d9b

ArthurZucker commented on 2023-10-18

Merge branch 'main' into flash_attn_starcoder

4792b337

younesbelkada commented on 2023-10-30

remove padding_mask

22a64cbb

susnato requested a review from

younesbelkada 2 years ago

younesbelkada commented on 2023-10-30

younesbelkada requested a review from

amyeroberts 2 years ago

younesbelkada approved these changes on 2023-10-30

change getattr->hasattr logic

ba0de166

amyeroberts approved these changes on 2023-10-30

changed .md file

d577b4f9

amyeroberts merged b5db8ca6 into main 2 years ago

sohamparikh commented on 2023-10-31

Reviewers

ArthurZucker

younesbelkada

amyeroberts

Ltrack

sohamparikh

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

transformers Add flash attention for `gpt_bigcode` #26479 Merged

Add flash attention for `gpt_bigcode` #26479

transformers
Add flash attention for `gpt_bigcode`
#26479

Merged