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). @ rejection_sampling_kernels

AlpinDale 0dfa6b60ec core: support logprobs with multi-step scheduling (#963)		il y a 1 mois
..
__init__.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	il y a 4 mois
loader.py	6bdff60aab quant: support pre-quanted bitsandbytes checkpoints (#961)	il y a 1 mois
neuron.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	il y a 1 mois
openvino.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	il y a 1 mois
tensorizer.py	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	il y a 1 mois
utils.py	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	il y a 1 mois
weight_utils.py	59d1d59028 api: support aphrodite_config.yaml with inline loading (#929)	il y a 1 mois