Prefix-Aware Attention for LLM Decoding
Python 54 3
🚀 Efficient linear attention kernels for Ascend NPUs
C++ 82 110
Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading
Python 16
Faster Gradient Computation for Delta-Rule Attention Family
Python 17
[ICML'26] MOSAIC: Unlocking Over 30× Context Length for Diffusion LLMs Inference via Global Memory Planning and Dynamic Peak Taming
An Open-Source RAG Workload Trace to Optimize RAG Serving Systems
Loading…
There was an error while loading. Please reload this page.