Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

truespar/paddock

Native Rust inference server for open models on NVIDIA and Apple Silicon. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio

Owner
truespar (organization)
Stars
Stars: 158
Forks
Forks: 25
Language
Rust
License
None
Created
2026
Topics
aiaimodelsinferenceinference-engineinference-optimizationrustblackwellcudamodel-servingnvidia
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by truespar

All 2 repos by truespar

Nearby in Rust

All Rust repos