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 85a865cc00 feat: fp8 quant		7 hónapja
..
guided_decoding	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
layers	85a865cc00 feat: fp8 quant	7 hónapja
models	fc80f57967 fix: correct file name for qwen2 moe	7 hónapja
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
hf_downloader.py	85a865cc00 feat: fp8 quant	7 hónapja
loader.py	85a865cc00 feat: fp8 quant	7 hónapja
neuron_loader.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
sampling_metadata.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja