arXiv (All)
open access
PulseInfer: I/O-Centric Sparse KV Cache Offloading for Efficient Long-Context LLM Decoding
Long-context LLM serving is increasingly bottlenecked by decode, where large KV caches limit batch size and underutilize GPUs. Sparse KV cache offloading expands effective capacity by storing most historical KV blocks in CPU DRAM and recalling only selected blocks on demand. However, we find that ex
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression#1033751
- Closer in the Gap: Towards Portable Performance on RISC-V Vector Processors#175193
- The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks#1043173
- The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks#793849
- What Governs Decode Throughput in Absolute-Offset GPU LZ77? A Work-Granularity Mechanism and an Encode-Time Min-Match-Length Lever#386825
Record · ID 1128820
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive