[`Llama ROPE`] Fix torch export but also slow downs in forward #29198
remove control flow
c72d04c0
update gptneox
9c6a8777
update ....
d04c6975
nits
614b8c35
Actually let's just break. Otherwise we are silently failing which im…
9c3c6f5e
version BC
12d60c62
fix tests
0fcd9ad3
ArthurZucker
marked this pull request as ready for review 2 years ago
gante
approved these changes
on 2024-02-22
fix eager causal
3eeef21f
Merge branch 'main' of github.com:huggingface/transformers into llama…
0df9d474
nit
d95f3ed4
Merge branch 'main' of github.com:huggingface/transformers into llama…
aec200ab
add a test
4a73df12
style
4323e414
nits
7f5ac69d
nits
b7d1884d
more nits for the test
100ab52e
update and fix
ca82c260
make sure cuda graphs are not skipped
409d97e4
read token is needed for meta llama
6b849368
update!
a01d0e18
fiixup
7e2c08bf
compile test should be slow
0809a9f1
ArthurZucker
changed the title [`Llama ROPE`] Export but also slow down in forward. [`Llama ROPE`] Fix torch export but also slow downs in forward 2 years ago
Merge branch 'main' of github.com:huggingface/transformers into llama…
6f2823cd
fix thet fix copies
5cfa3fbd
stle 🫠
14db98ef
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub