Nicolas Patry 1da07e85aa feat(server): Add Non flash MPT. (#514) ... # What does this PR do? This adds a non flash version of MPT. Flash is harder because we need to create a bias ready cuda kernel of flash attention. Fixes https://github.com/huggingface/text-generation-inference/issues/361 Fixes https://github.com/huggingface/text-generation-inference/issues/491 Fixes https://github.com/huggingface/text-generation-inference/issues/290		2023-07-03 13:01:46 +02:00
..
__init__.py	feat(server): flash santacoder (#153)	2023-04-03 19:06:42 +02:00
bloom_modeling.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
flash_llama_modeling.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00
flash_neox_modeling.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00
flash_rw_modeling.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00
flash_santacoder_modeling.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00
mpt_modeling.py	feat(server): Add Non flash MPT. (#514)	2023-07-03 13:01:46 +02:00
neox_modeling.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
opt_modeling.py	feat(server): Rework model loading (#344)	2023-06-08 14:51:52 +02:00
t5_modeling.py	feat(server): add paged attention to flash models (#516)	2023-06-30 19:09:59 +02:00