Tag
Photon 2.0 is a new inference engine and compiler that compiles models like Moondream, Qwen 3.5, and Gemma 4 into megakernels, claiming up to 2.3x throughput over vLLM and SGLang for physical AI workloads.
This paper demonstrates that agentic workflows can be distilled into small fine-tuned models, achieving near-frontier quality while reducing inference cost by two orders of magnitude compared to orchestration approaches.