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). @ multi-step

AlpinDale 2242841380 add to benchmark		4 месяцев назад
..
latency.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 месяцев назад
serving.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 месяцев назад
throughput.py	2242841380 add to benchmark	4 месяцев назад