Hugging Face's logo
Dan Petrovic's picture
💼 Hiring

Dan Petrovic PRO

dejanseo
44 6 100
adamfallon's profile picture Mi6paulino's profile picture Aifanatic123's profile picture
·
https://dejan.ai/

AI & ML interests

DEJAN - The AI SEO agency. [DEJAN](https://dejan.ai/)

Recent Activity

posted an update about 11 hours ago
10 Search Subqueries in 200 Microseconds: 1-Bit Consistency Fanout We built Fanout Diffusion, an ultra-low-latency model that expands a search query into 10 diverse subquery vectors in a single forward pass. Inspired by the continuous retrieval framework in R4T (arXiv:2603.06397), our goal was to make query expansion fast enough for production search without running language models. How it works: • Direct Embedding Space: Takes a query embedded via google/embeddinggemma-300m (768-dim) and predicts 10 distinct subquery vectors simultaneously. • 1-Step Consistency Denoiser: Generates all 10 slots analytically in a single pass with zero ODE integration loops. • 1-Bit Hardware Tensor Cores: Quantized ternary weights (-1, 0, +1) running on Ampere/Ada sub-byte PTX instructions with INT4 outer projections. Key numbers on an RTX 4090: • Latency: 0.200 ms (ONNX) / 0.329 ms (native C++ CUDA graph) • Throughput: 417,035 queries/second in batch mode • Model Size: 1.64 MB (PyTorch QAT) / 32.1 MB (ONNX graph) • Quality: 0.683 prompt alignment across 540k search queries Interactive Space: https://huggingface.co/spaces/dejanseo/fanout-diffusion Model weights, ONNX graph, and C++ engine: https://huggingface.co/dejanseo/fanout-diffusion
updated a Space about 11 hours ago
dejanseo/fanout-diffusion
updated a model about 11 hours ago
dejanseo/fanout-diffusion
View all activity

Organizations

Dejan Marketing's profile picture Blog-explorers's profile picture