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 2aabf8fcf7 vlm: fix errors on ragged NestedTensors (#953)		1 månad sedan
..
__init__.py	8b42b58228 vlm: stack multimodal tensors to represent multiple images within each prompt (#937)	1 månad sedan
audio.py	3693028340 feat: support for Audio modality (#698)	4 månader sedan
base.py	2aabf8fcf7 vlm: fix errors on ragged NestedTensors (#953)	1 månad sedan
image.py	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	1 månad sedan
registry.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	4 månader sedan
utils.py	03bd85c950 chore: multi-image support for llava-next (#935)	1 månad sedan