Nicolas Patry 5ca0508d02 Simpler exllama		2023-07-20 15:36:53 +00:00
..
custom_modeling	Simpler exllama	2023-07-20 15:36:53 +00:00
__init__.py	feat(server): flash attention v2 (#624)	2023-07-18 16:21:18 +02:00
bloom.py	feat: Add the option to force another dtype than f16. (#513)	2023-06-30 20:30:09 +02:00
causal_lm.py	Simpler exllama	2023-07-20 15:36:53 +00:00
flash_causal_lm.py	Simpler exllama	2023-07-20 15:36:53 +00:00
flash_llama.py	Simpler exllama	2023-07-20 15:36:53 +00:00
flash_neox.py	Simpler exllama	2023-07-20 15:36:53 +00:00
flash_rw.py	Simpler exllama	2023-07-20 15:36:53 +00:00
flash_santacoder.py	Simpler exllama	2023-07-20 15:36:53 +00:00
galactica.py	Simpler exllama	2023-07-20 15:36:53 +00:00
gpt_neox.py	Simpler exllama	2023-07-20 15:36:53 +00:00
model.py	Simpler exllama	2023-07-20 15:36:53 +00:00
mpt.py	Simpler exllama	2023-07-20 15:36:53 +00:00
opt.py	Simpler exllama	2023-07-20 15:36:53 +00:00
rw.py	Simpler exllama	2023-07-20 15:36:53 +00:00
santacoder.py	Simpler exllama	2023-07-20 15:36:53 +00:00
seq2seq_lm.py	Simpler exllama	2023-07-20 15:36:53 +00:00
t5.py	Simpler exllama	2023-07-20 15:36:53 +00:00
types.py	feat(server): support vectorized warpers in flash causal lm (#317)	2023-05-26 12:30:27 +02:00