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). @ prompt_logprobs_mem

AlpinDale 22a4cd4595 core: fix spec decode metrics and envs circular import (#889)		vor 1 Monat
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
cuda_wrapper.py	9c0e7d95c8 fix: libcudart path for some versions of pytorch (#726)	vor 4 Monaten
custom_all_reduce.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	vor 1 Monat
custom_all_reduce_utils.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	vor 1 Monat
pynccl.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
pynccl_wrapper.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
shm_broadcast.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	vor 1 Monat
tpu_communicator.py	8878e3a63f fix: import ray under a guard (#708)	vor 4 Monaten