#inference
1 note or post, 2 links.
Notes and posts
LLM Inference
LLM Inference in Production by BentoML; "core concepts and performance metrics, to optimization techniques and operation best practices"
Links Open in the Archive
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
Introduction | LLM Inference in Production