david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ c3b15f0926dd24885d9f780f01a451d26fd52653

AlpinDale a788ca33bf hack in custom bias for attention kernels		пре 9 месеци
..
__init__.py	a788ca33bf hack in custom bias for attention kernels	пре 9 месеци
baichuan.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
bloom.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
chatglm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	пре 10 месеци
cohere.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
decilm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	пре 10 месеци
deepseek.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
falcon.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
gemma.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
gpt2.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
gpt_bigcode.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
gpt_j.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
gpt_neox.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
internlm2.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
llama.py	6ebac34dc1 chore: cleaner pre-llamafied Yi implementation (#352)	пре 9 месеци
mixtral.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
mixtral_quant.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
mpt.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
olmo.py	e42a78381a feat: switch from pylint to ruff (#322)	пре 10 месеци
opt.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
phi.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
qwen.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
qwen2.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
stablelm.py	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	пре 9 месеци
t5.py	f009f94ffd update modeling code	пре 9 месеци