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). @ 1d7f5c45b0373887c9cc88a69a2413b32d7d5303

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