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