memory-efficiency
Flash-dLLM
[NeurIPS 2026] Official implementaion for Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
- 20
- Python
- Apache-2.0
- 7 wk ago
[NeurIPS 2026] Official implementaion for Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs