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). @ 39beed0b87cbbd93bad2b11b939a15941cf67f6f

AlpinDale 39beed0b87 Revert "Refactor AWQ support."		1 éve
..
tensor_parallel	39beed0b87 Revert "Refactor AWQ support."	1 éve
README.md	386be46787 fix: megatron-lm url	1 éve
__init__.py	76b2e4a445 Merge dev branch into main (#7)	1 éve
parallel_state.py	4be81db3d4 chore: adapt the megatron code for parallelism	1 éve

The files here are from the NVIDIA Megatron-LM repository, but only with inference-related code.