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). @ e13a66925cf2d117b26d0e062e2c62f82dc7f7dd

AlpinDale e13a66925c feat: add fuyu vision model and persimmon language model support		6 bulan lalu
..
guided_decoding	c25a9abb28 fix: outlines failing on second launch	6 bulan lalu
layers	1efd0f89b7 feat: support FP8 for DeepSeekV2 MoE	6 bulan lalu
model_loader	4f7d212b70 feat: remove vision language config	6 bulan lalu
models	e13a66925c feat: add fuyu vision model and persimmon language model support	6 bulan lalu
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 bulan lalu
_custom_op.py	b6ff0623a6 chore: clean up branding	7 bulan lalu
pooling_metadata.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	7 bulan lalu
sampling_metadata.py	63b735bc2a chore: optimize v2 block manager to match the performance of v1	7 bulan lalu
utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	10 bulan lalu