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). @ sampling-kernels

AlpinDale 45a004874c chore: allow specifying custom Executor		hace 4 meses
..
configs	d9f4c36edd feat: Medusa speculative decoding support (#590)	hace 4 meses
tokenizer_group	45a004874c chore: allow specifying custom Executor	hace 4 meses
tokenizers	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	hace 9 meses
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	hace 1 año
config.py	d9f4c36edd feat: Medusa speculative decoding support (#590)	hace 4 meses
detokenizer.py	a26f784240 chore: use the LoRA tokenizer in OpenAI API (#599)	hace 4 meses
image_processor.py	4599c98f99 feat: dynamic image size support for VLMs	hace 4 meses
tokenizer.py	a26f784240 chore: use the LoRA tokenizer in OpenAI API (#599)	hace 4 meses