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."		hai 1 ano
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	hai 1 ano
activation.py	32844c1522 add GELU kernels and remove compile bloat	hai 1 ano
attention.py	e77960c57e use float datatype for RoPE	hai 1 ano
layernorm.py	f2fe14ec1c fix: epsilon variance value for RMSNorm	hai 1 ano
sampler.py	6dfca14e1f compute logprobs with log_softmax instead of log	hai 1 ano