huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 07:52:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
f3435bab8c
text-generation-inference/server/text_generation_server/layers/attention
History
OlivierDehaene 53ec0b790b
feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 
* feat(fp8): add support for fbgemm

* allow loading fp8 weights directly

* update outlines

* fix makefile

* build fbgemm

* avoid circular import and fix dockerfile

* add default dtype

* refactored weights loader

* fix auto conversion

* fix quantization config parsing

* force new nccl on install

* missing get_weights implementation

* increase timeout
2024-07-20 19:02:04 +02:00
..
__init__.py [Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940) 2024-07-01 23:28:00 +02:00
common.py [Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940) 2024-07-01 23:28:00 +02:00
cuda.py [Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940) 2024-07-01 23:28:00 +02:00
flash_attn_triton.py Purely refactors paged/attention into layers/attention and make hardware differences more obvious with 1 file per hardware. (#1986) 2024-05-31 17:57:01 +02:00
ipex.py fix FlashDecoding change's regression in intel platform (#2161) 2024-07-02 11:56:07 +02:00
rocm.py feat(fp8): use fbgemm kernels and load fp8 weights directly (#2248) 2024-07-20 19:02:04 +02:00