工具POST
Husky: an inference engine up to 4.5x faster than Apple MLX
Underdog introduced Husky, a model-specific inference engine it says is up to 4.5x faster than Apple's MLX and focused on Pareto-frontier performance.
Marc Andreessen 🇺🇸
@pmarcaArchived 2026.09.22Originally posted 2026.09.22
Marc Andreessen 🇺🇸 @pmarcaOriginally posted 2026.09.22
RT @0xSigil: Meet Husky: a Model-Specific Inference (MSI) engine up to 4.5× faster than Apple's MLX Woof, Underdog's Pareto frontier mod…
x.com/pmarca/status/2102169085857746992Archived 2026.09.22 10:36