⚡ 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
Measurement harness for the sliding window attention premium in the vLLM TPU Ragged Paged Attention v3 kernel: per layer decode cost, block size control, throughput, and goodput for Gemma 4 31B on TPU v6e.
A high-performance terminal-integrated LLM engine in Rust
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
ViT with Hilbert-curve patch ordering for better 2D locality in sliding-window attention. PyTorch.
Analytical benchmark for sliding window attention KV cache management: quality vs window size tradeoffs, SWA vs eviction comparison, prefix sharing interaction, and operational window recommendations across four attention distributions
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."