QSA HiSparse as an SGLang plugin: 256K CPU KV offload and text/image host prefix reuse for Qwen Sparse Attention on unmodified SGLang
-
Updated
Oct 9, 2026 - Python
QSA HiSparse as an SGLang plugin: 256K CPU KV offload and text/image host prefix reuse for Qwen Sparse Attention on unmodified SGLang
A MATLAB-based program for processing and analysis of nanoSIMS data
Coleção do Postman para as APIs do Consultar.IO
Consulta ágil de dados corporativos e extração de QSA (Quadro Societário) via CNPJ.
A modern dom selector based on next toolkit.
From-scratch SM80 (A100/A800) CUDA kernels for GDN (Gated DeltaNet) and QSA (query-key sparse attention). Apache-2.0.
To associate your repository with the qsa topic, visit your repo's landing page and select "manage topics."