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). @ fp8-quant

AlpinDale fc80f57967 fix: correct file name for qwen2 moe		vor 8 Monaten
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
baichuan.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
bloom.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
chatglm.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
cohere.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
dbrx.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
decilm.py	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	vor 11 Monaten
deepseek.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
falcon.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
gemma.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
gpt2.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
gpt_bigcode.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
gpt_j.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
gpt_neox.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
internlm2.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
llama.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
llava.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
mixtral.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
mpt.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
olmo.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
opt.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
phi.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
qwen.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
qwen2.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
qwen2_moe.py	fc80f57967 fix: correct file name for qwen2 moe	vor 8 Monaten
stablelm.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten