Spanda
Sub-microsecond LLM epistemic uncertainty in Rust. Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy).
Open source
Reactions (1)
Similar products
by description similarity
An educational Rust project for exporting and running inference on Qwen3 LLM family
Speeding up LLM inference 2x times (possibly)
asciinema.orgHere's a project I've been working on for the last few months.
Picohsm
picokeys.coma $5 open-source hsm
TinyOS
github.comA minimalist RTOS for Cortex-M written in C
Metrics Observability & Troubleshooting