XM‑Sparse: Pushing the Throughput Frontier of Sparse Attention with Netpreme X‑Mem™
XM-Sparse integrates Netpreme X-Mem™ with SGLang HiSparse. High-bandwidth access to offloaded KV caches reduces decode latency, while the added capacity supports larger batches and higher concurrency. Sparse attention accesses only selected KV entries at each decode step, but still retains…