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). @ ec5b99d075c728d0ab4188ce1f277d24b45d389c

AlpinDale 5b5e6dc359 chore: add batch size 1536 and 3072 to moe benchmark		7 kuukautta sitten
..
attention.py	e1f3fd1e02 fix: test units (#201)	1 vuosi sitten
backend_request_func.py	89ee54dcff update dockerfile and enhance serving benchmark	7 kuukautta sitten
benchmark_moe.py	5b5e6dc359 chore: add batch size 1536 and 3072 to moe benchmark	7 kuukautta sitten
hashing.py	c6a501f682 add multiprocessing executor; make ray optional	7 kuukautta sitten
latency.py	e1f3fd1e02 fix: test units (#201)	1 vuosi sitten
launch_tgi.sh	4d04ade9ef feat: fine-grained seeds (#279)	1 vuosi sitten
serving.py	89ee54dcff update dockerfile and enhance serving benchmark	7 kuukautta sitten
sonnet.txt	89ee54dcff update dockerfile and enhance serving benchmark	7 kuukautta sitten
throughput.py	033797fd55 refactor throughput benchmark script	7 kuukautta sitten