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). @ b02e6336918a09d1baaec124213acb0bbab3bc38

AlpinDale e7b1368156 feat: Phi3 support		vor 6 Monaten
..
__init__.py	e7b1368156 feat: Phi3 support	vor 6 Monaten
baichuan.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
bloom.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
chatglm.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
commandr.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
dbrx.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
decilm.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
deepseek.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
falcon.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
gemma.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
gpt2.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
gpt_bigcode.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
gpt_j.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
gpt_neox.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
internlm2.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
jais.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
llama.py	e7b1368156 feat: Phi3 support	vor 6 Monaten
llava.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
minicpm.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
mixtral.py	46159b107a formatting: pt1	vor 6 Monaten
mixtral_quant.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
mpt.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
olmo.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
opt.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
orion.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
phi.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
qwen.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
qwen2.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
qwen2_moe.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
stablelm.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
starcoder2.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten
xverse.py	fca911ee0a vLLM Upstream Sync (#526)	vor 6 Monaten