Decision 3.0 — Core ML

Decision 3.0 by the vLLM Semantic Router team, converted to Core ML for Apple silicon: text, image and video requests on device. Same contract as upstream: one forward pass per question, the 255-way FP32 readout at the last prompt token, a probability for every option, no text generated.

Each folder is a full release (text graphs, vision tower, host tables, Python host) with its own README covering files, parity against upstream and speed. Swift: D3VisionManager in FluidUse loads any of them.

License: Apache-2.0, as upstream.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for FluidInference/d3-coreml

Finetuned
vllm-sr/d3-lite
Quantized
(5)
this model