An optimized inference engine to turn LLMs into Jev-like machines: optimized for quick, lightweight, and accurate decision-making, classification, and scoring
Stars measure the whole repository, including work unrelated to Jev.
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
- All cases contain one decision, so this test does not measure multi-field parallel scaling. These are our local CUDA measurements, not the HF project's published Apple Silicon results. Jev was not benchmarked.
Evidence commit: 20c112e34cc01ba993eb875358443b6d1a64800c
Discovered through: awesome-jev.
How we review →