system-algorithm-deisgn

Here are 4 public repositories matching this topic...

SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling

[ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

efficient llm system-algorithm-deisgn

This is a research project to efficiently accelerate speculative decoding with token-level cross-paradigm routing, accepted at EMNLP 2026.

This is a research project to efficiently compress diffusion models, accepted at AAAI 2026.

To associate your repository with the system-algorithm-deisgn topic, visit your repo's landing page and select "manage topics."