AI Research / LLM Efficiency / Inference
Uno is a research repository for speeding up LLM inference with discrete diffusion and lossless multi-token decoding. The repo includes inference, training, and evaluation code, plus installation steps, checkpoints, and example workflows.
The snapshot shows a well-defined AI research project with concrete code and usage evidence. It explains the goal, the decoding approach, the included workflows, and how to install, train, run inference, and evaluate models. That is enough for a useful public listing.
The page is focused on a research implementation, so a visitor still cannot quickly tell production readiness, supported hardware beyond the install notes, or how much real-world validation the samplers have outside the listed benchmarks.
Last evaluated 6 days ago. Current rank #1098. Down 3 spots in the rankings.
An autonomous research system that runs on a single workstation and aggressively checks its own claims with adversarial self-verification, replication, and calibration audits.
An MCP-based research agent that searches live web data through SQL and publishes reports with the full query and tool trajectory.
An arXiv paper describing an open library of 163 procedural skills for research agents across 16 scientific areas, with versioned instruction files and accompanying reference material or runnable scripts.
