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). @ c1fa7e856723fc178663fd34d22b28fa2f95fc03

AlpinDale 044251018e chore: update readme and the tests		1 年之前
..
engine	0f4c50eafb feat: add detokenize test suite	1 年之前
kernels	b20083a1f3 feat: finish kernel testing	1 年之前
models	3738f09886 feat: add model and sampler tests	1 年之前
samplers	3738f09886 feat: add model and sampler tests	1 年之前
latency.py	044251018e chore: update readme and the tests	1 年之前
serving.py	044251018e chore: update readme and the tests	1 年之前
throughput.py	6be8855494 fix: add GPTQ to throughput test	1 年之前