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). @ ad1c6b86a1fa85e28c0a3e177a46f481d0cc4642

AlpinDale 033797fd55 refactor throughput benchmark script		7 月之前
..
attention.py	e1f3fd1e02 fix: test units (#201)	1 年之前
backend_request_func.py	e42a78381a feat: switch from pylint to ruff (#322)	1 年之前
hashing.py	c6a501f682 add multiprocessing executor; make ray optional	7 月之前
latency.py	e1f3fd1e02 fix: test units (#201)	1 年之前
launch_tgi.sh	4d04ade9ef feat: fine-grained seeds (#279)	1 年之前
moe_config.py	6d2f00d728 benchmark script for fp8 MoE	7 月之前
serving.py	e42a78381a feat: switch from pylint to ruff (#322)	1 年之前
throughput.py	033797fd55 refactor throughput benchmark script	7 月之前