transformers
Add padding-free to bamba
#35861
Merged

Add padding-free to bamba #35861

garrett361
garrett361 garrett361 force pushed from cdaf1e6d to eab1ae12 1 year ago
garrett361 garrett361 closed this 1 year ago
garrett361 garrett361 reopened this 1 year ago
garrett361 garrett361 force pushed from eab1ae12 to c4874af4 1 year ago
Rocketknight1
garrett361
garrett361 garrett361 force pushed from 49d007c9 to d35bcc68 1 year ago
garrett361
garrett361 garrett361 force pushed from d35bcc68 to 7a9e3433 1 year ago
garrett361 garrett361 force pushed from 9577fb44 to 0534b8f5 1 year ago
garrett361 garrett361 force pushed from 2eda0a70 to dfaca139 1 year ago
garrett361 garrett361 force pushed from dfaca139 to 5d39d5e9 1 year ago
garrett361
ArthurZucker
ArthurZucker commented on 2025-02-05
garrett361 garrett361 force pushed from 5d39d5e9 to 6fdd9a04 1 year ago
garrett361
ArthurZucker
ArthurZucker commented on 2025-02-06
garrett361
vasqu
vasqu commented on 2025-02-06
garrett361
ArthurZucker
ArthurZucker commented on 2025-02-19
garrett361
garrett361
garrett361
garrett361 garrett361 force pushed from bc275139 to 9fc336bc 1 year ago
garrett361 garrett361 force pushed from 539f1bb3 to 6260a005 1 year ago
garrett361
vasqu
vasqu commented on 2025-03-04
vasqu
vasqu commented on 2025-03-04
garrett361 garrett361 force pushed from 83cc8b7a to a30d09e4 1 year ago
garrett361 garrett361 closed this 1 year ago
garrett361 garrett361 force pushed from a30d09e4 to 5b573beb 1 year ago
garrett361 garrett361 reopened this 1 year ago
github-actions github-actions marked this pull request as draft 1 year ago
github-actions
garrett361 garrett361 marked this pull request as ready for review 1 year ago
garrett361
vasqu
vasqu
vasqu approved these changes on 2025-05-04
vasqu
vasqu commented on 2025-05-05
garrett361
garrett361
ArthurZucker
ArthurZucker commented on 2025-05-20
garrett361
garrett361
garrett361
garrett361 add seq_idx and fa kwargs
810e69a1
garrett361 update tests
fc162216
garrett361 docs and grad ckpt support
12930277
garrett361 fmt
e9fd9862
garrett361 better names
a8a953d5
garrett361 test_raise_missing_padding_free_kwarg_errs
ea6b8bf4
garrett361 + seq_idx in doc strings
f978ca20
garrett361 padding free training docs
2350e541
garrett361 add link to pr plots
b73c1a1e
garrett361 raise err on attn_mask with padding free
a6627e0d
garrett361 rm raising missing padding free err test
a47588ae
garrett361 garrett361 force pushed from bfc123df to 56f508f3 1 year ago
garrett361
garrett361 BambaFlashAttentionKwargs
b59e5c96
garrett361 garrett361 force pushed from 56f508f3 to b59e5c96 1 year ago
ArthurZucker
ArthurZucker approved these changes on 2025-05-20
garrett361
garrett361 run modular util for modular_granitemoehybrid.py
289d2045
HuggingFaceDocBuilderDev
garrett361
ArthurZucker ArthurZucker merged 390f1534 into main 1 year ago
ArthurZucker
garrett361
vasqu
garrett361

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone