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). @ c1c37c755d5df53397610c6e7fc316db0898cd15

AlpinDale 4d4e767838 ci: take one of fixing lint issues		5 månader sedan
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 månader sedan
cuda_wrapper.py	cc6399792f fix: keep consistent with how pytorch finds libcudart.so	5 månader sedan
custom_all_reduce.py	4d4e767838 ci: take one of fixing lint issues	5 månader sedan
custom_all_reduce_utils.py	4d4e767838 ci: take one of fixing lint issues	5 månader sedan
pynccl.py	6b1fdd07bd chore: add isort and refactor formatting script and utils	5 månader sedan
pynccl_wrapper.py	f91991f584 fix: f-string fixes	5 månader sedan
shm_broadcast.py	bcd8e72dbd fix: zmq hangs with large requests	5 månader sedan
tpu_communicator.py	8d88814475 chore: reduce XLA compile times	5 månader sedan