Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/server/text_generation_server/layers/attention
History
drbh 215ed3ad52
fix: attempt forward on flash attn2 to check hardware support (#2335) 
* fix: attempt forward on flash attn2 to check hardware support

* fix: warn window_size_left when using flash attn 1

* fix: prefer version check over test op and avoid window_size_left if not flash attn2

* fix: improve condtional and error message

* fix: update sliding window conditional

* fix: simplify changes and revert model changes

* fix: avoid changing conditional

* fix: typo tweak
 		2024-08-05 09:11:40 -04:00
..
__init__.py feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
common.py [Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940) 2024-07-01 23:28:00 +02:00
cuda.py fix: attempt forward on flash attn2 to check hardware support (#2335) 2024-08-05 09:11:40 -04:00
flash_attn_triton.py feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
ipex.py Unify attention output handling (#2343) 2024-08-01 17:03:28 +02:00
rocm.py Unify attention output handling (#2343) 2024-08-01 17:03:28 +02:00