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). @ e2dbe5f05c6080dd961d492a35dd21a0a450ab41

AlpinDale 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)		7 bulan lalu
..
attention.py	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	7 bulan lalu
backend_request_func.py	89ee54dcff update dockerfile and enhance serving benchmark	7 bulan lalu
benchmark_moe.py	5b5e6dc359 chore: add batch size 1536 and 3072 to moe benchmark	7 bulan lalu
hashing.py	c6a501f682 add multiprocessing executor; make ray optional	7 bulan lalu
latency.py	e1f3fd1e02 fix: test units (#201)	1 tahun lalu
launch_tgi.sh	4d04ade9ef feat: fine-grained seeds (#279)	1 tahun lalu
serving.py	89ee54dcff update dockerfile and enhance serving benchmark	7 bulan lalu
sonnet.txt	89ee54dcff update dockerfile and enhance serving benchmark	7 bulan lalu
throughput.py	033797fd55 refactor throughput benchmark script	7 bulan lalu