rattus ae79e33345 llama: use a more efficient rope implementation (#12434) ... Get rid of the cat and unary negation and inplace add-cmul the two halves of the rope. Precompute -sin once at the start of the model rather than every transformer block. This is slightly faster on both GPU and CPU bound setups.		2026-02-12 19:56:42 -05:00
..
ace_lyrics_tokenizer
byt5_tokenizer
hydit_clip_tokenizer
llama_tokenizer
qwen25_tokenizer
t5_pile_tokenizer
t5_tokenizer
ace15.py	Update ace15.py to allow min_p sampling (#12373)	2026-02-11 20:28:48 -05:00
ace_text_cleaners.py
ace.py
anima.py	Fix bug with last pr (#12338)	2026-02-06 19:48:20 -05:00
aura_t5.py
bert.py
byt5_config_small_glyph.json
cosmos.py
flux.py	Enable embeddings for some qwen 3 models. (#12218)	2026-02-02 03:51:09 -05:00
genmo.py
hidream.py
hunyuan_image.py
hunyuan_video.py	Support loading flux 2 klein checkpoints saved with SaveCheckpoint. (#12033)	2026-01-22 18:20:48 -05:00
hydit_clip.json
hydit.py
jina_clip_2.py
kandinsky5.py
llama.py	llama: use a more efficient rope implementation (#12434)	2026-02-12 19:56:42 -05:00
long_clipl.py
lt.py	Disable prompt weights for ltxv2. (#12354)	2026-02-07 19:16:28 -05:00
lumina2.py
mt5_config_xl.json
newbie.py
omnigen2.py
ovis.py
pixart_t5.py
qwen_image.py
qwen_vl.py
sa_t5.py
sd2_clip_config.json
sd2_clip.py
sd3_clip.py
spiece_tokenizer.py
t5_config_base.json
t5_config_xxl.json
t5_old_config_xxl.json
t5_pile_config_xl.json
t5.py
umt5_config_base.json
umt5_config_xxl.json
wan.py
z_image.py	Enable embeddings for some qwen 3 models. (#12218)	2026-02-02 03:51:09 -05:00