SpecBundle Collection A collection of production-grade draft models for speculative decoding • 30 items • Updated 2 days ago • 19
SpecBundle Collection A collection of production-grade draft models for speculative decoding • 30 items • Updated 2 days ago • 19
SpecBundle Collection A collection of production-grade draft models for speculative decoding • 30 items • Updated 2 days ago • 19
Diffusion ModelOpt Collection SGLang-native diffusion transformer overrides converted with NVIDIA ModelOpt. • 12 items • Updated Jun 23 • 1