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). @ 639e48e47d9c03619c540f76d90509290ee77c19

AlpinDale f22b700ee4 feat: marlin kernels for GPTQ (#547)		преди 8 месеца
..
attention.py	e1f3fd1e02 fix: test units (#201)	преди 1 година
backend_request_func.py	e42a78381a feat: switch from pylint to ruff (#322)	преди 1 година
latency.py	e1f3fd1e02 fix: test units (#201)	преди 1 година
launch_tgi.sh	4d04ade9ef feat: fine-grained seeds (#279)	преди 1 година
moe_config.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	преди 1 година
serving.py	e42a78381a feat: switch from pylint to ruff (#322)	преди 1 година
throughput.py	f22b700ee4 feat: marlin kernels for GPTQ (#547)	преди 8 месеца