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). @ feat/jamba-support

AlpinDale b1caee23a6 cache the p2p access check for memory saving		hace 9 meses
..
__init__.py	8db2fa8e2e why was that not committed?	hace 9 meses
custom_all_reduce.py	b1caee23a6 cache the p2p access check for memory saving	hace 9 meses
pynccl.py	50c2434267 move megatron to a top-level directory	hace 9 meses
pynccl_utils.py	50c2434267 move megatron to a top-level directory	hace 9 meses