Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.
The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!
This repository provides the official implementation of TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by $100 \sim 200\times$ on a single RTX 5090, while maintaining video quality. TurboDiffusion primarily uses SageAttention, SLA (Sparse-Linear Attention) for attention acceleration, and rCM for timestep distillation.
Full detail backing SKILL.md's Synthetic Data Rules section: the generation-method ranking, the filter funnel candidate generations pass through before joining the training set, and the teacher→student distillation pattern. Base models are never named as recommendations here. Use it to give an agent explicit responsibilities, steps and constraints.
The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!
This repository provides the official implementation of TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by $100 \sim 200\times$ on a single RTX 5090, while maintaining video quality. TurboDiffusion primarily uses SageAttention, SLA (Sparse-Linear Attention) for attention acceleration, and rCM for timestep distillation.