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). @ multinode_dynatemp

AlpinDale 36660b55c2 chore: mixtral fp8 w/ static scales (#542)		преди 5 месеца
..
__init__.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
baichuan.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
bloom.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
chatglm.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
commandr.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
dbrx.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
decilm.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
deepseek.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
falcon.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
gemma.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
gpt2.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
gpt_bigcode.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
gpt_j.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
gpt_neox.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
internlm2.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
jais.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
llama.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
llava.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
minicpm.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
mixtral.py	36660b55c2 chore: mixtral fp8 w/ static scales (#542)	преди 5 месеца
mixtral_quant.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
mpt.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
olmo.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
opt.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
orion.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
phi.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
qwen.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
qwen2.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
qwen2_moe.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
stablelm.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
starcoder2.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца
xverse.py	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	преди 5 месеца