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). @ sampling-kernels

AlpinDale f91991f584 fix: f-string fixes		5 mesi fa
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 mesi fa
cuda_wrapper.py	cc6399792f fix: keep consistent with how pytorch finds libcudart.so	5 mesi fa
custom_all_reduce.py	f91991f584 fix: f-string fixes	5 mesi fa
custom_all_reduce_utils.py	2c321ce1f2 chore: upgrade to rocm 6.1, update docker	5 mesi fa
pynccl.py	e238abf0cc chore: send and recv helper functions	5 mesi fa
pynccl_wrapper.py	f91991f584 fix: f-string fixes	5 mesi fa
shm_broadcast.py	c92e46af58 fix shared memory bug w/ multi-node	5 mesi fa