mrq aee08b7307 changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)		2024-11-03 09:58:29 -06:00
..
emb	saner mask creation? (it doesnt matter, kv cache wont work)	2024-11-02 21:00:21 -05:00
engines	ughh	2024-11-01 22:36:48 -05:00
ext
models	changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)	2024-11-03 09:58:29 -06:00
utils
__init__.py
__main__.py	shuffled web UI options hidden by cfg.experimental to its own tab, expose early exit selection to inferencing (it kinda works naively, still need to implement self-speculation)	2024-11-01 21:30:06 -05:00
config.py
data.py	saner mask creation? (it doesnt matter, kv cache wont work)	2024-11-02 21:00:21 -05:00
demo.py	changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)	2024-11-03 09:58:29 -06:00
export.py
inference.py	changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)	2024-11-03 09:58:29 -06:00
plot.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
samplers.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00
train.py	changed layerskip float16 training warning (since it didnt seem to fry on my 4xV100 system)	2024-11-03 09:58:29 -06:00
webui.py	very, very naive layerskip speculative sampling (it just checks if the current layer's state is good enough)	2024-11-02 11:49:05 -05:00