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). @ feat/perplexity

drummerv e59dd4a90d fix: openai gguf chat template (#312)		il y a 10 mois
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	il y a 1 an
api_server.py	e59dd4a90d fix: openai gguf chat template (#312)	il y a 10 mois
protocol.py	769b069e2e AttributeError fix in OpenAI server	il y a 10 mois
samplers.json	ac82b67f75 feat: naive context shift and various QoL changes (#289)	il y a 10 mois
serving_chat.py	c2d77b1822 chore: logging refactor (#302)	il y a 10 mois
serving_completions.py	c2d77b1822 chore: logging refactor (#302)	il y a 10 mois
serving_engine.py	c2d77b1822 chore: logging refactor (#302)	il y a 10 mois