arXiv (All)
open access
HERALD: High-Throughput Block Diffusion LLM Inference via CPU-GPU Cooperative KV Cache Retrieval
Block diffusion LLMs (block dLLMs) improve decode throughput by generating tokens in parallel, and are emerging as a next-generation alternative to autoregressive LLMs. At long contexts, however, the KV cache remains a major throughput bottleneck in both memory bandwidth and capacity. For autoregres
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
- Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale#999980
- ZipFusion: Fusing Lossless KV Decompression with Attention for Efficient LLM Decoding#1456542
- ZipFusion: Fusing Lossless KV Decompression with Attention for Efficient LLM Decoding#1450757
- DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution#1248564
- PhaseGate: Phase-Aware CPU Retrieval Scheduling for On-Device LLMs on Unified Memory#1200188
Record · ID 1537252
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