Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
4 results for “KV cache”
CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents
CommitKV is a new KV cache compression method for multi-turn ReAct agents that identifies and removes only truly completed information—distinguishing it from temporarily dormant but future-relevant data—thereby reducing memory use, speeding inference, and improving accuracy.
Aug 11, 2026
A requiem for Optane, Intel's KV cache killer that could have eased the RAM price crunch - The Register
Intel discontinued its Optane memory technology, a high-performance persistent memory and key-value cache solution that had potential to alleviate RAM supply constraints and pricing pressures but failed to achieve market traction.
Published Jul 28, 2026 · Analyzed Aug 1, 2026
SpecLA: Efficient Speculative Decoding for Linear-Attention Models
SpecLA is a new speculative decoding runtime designed specifically for linear-attention models, enabling up to 1.70x end-to-end speedup by addressing recurrent-state verification challenges that existing speculative systems ignore.
Jul 21, 2026
Kara: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression
Kara is a new sliding-window KV cache compression method for reasoning LLMs that improves decoding throughput and reduces memory overhead by selectively preserving flexible-sized semantic chunks of the key-value cache during inference.
Published Jul 3, 2026 · Analyzed Jul 6, 2026