⚡ Zero-Stall MoE Inference via Lookahead Prediction & Async DMA Prefetching. Optimized for SSD I/O with Hybrid MLA+Sliding Window Attention.
-
Updated
Apr 26, 2026 - Python
⚡ Zero-Stall MoE Inference via Lookahead Prediction & Async DMA Prefetching. Optimized for SSD I/O with Hybrid MLA+Sliding Window Attention.
Notes on the Mistral AI model
🚀 Sliding Window Attention Training for Efficient Large Language Models
Ring sliding window attention implementation with flash attention
A high-performance terminal-integrated LLM engine in Rust
ViT with Hilbert-curve patch ordering for better 2D locality in sliding-window attention. PyTorch.
Faithful from-scratch PyTorch reproduction of OpenAI's GPT-OSS architecture (sliding/full attention alternation, learned attention sinks, YaRN 128K, top-2-of-8 MoE), scaled to Chinchilla-optimal 502M total / 247M active training on a single A100 80GB
Add a description, image, and links to the sliding-window-attention topic page so that developers can more easily learn about it.
To associate your repository with the sliding-window-attention topic, visit your repo's landing page and select "manage topics."