arXiv (All)
open access
Accelerating CPU Speculative Decoding via Unified Graph Execution and Transactional KV Isolation
Speculative decoding accelerates LLM inference, but deploying it on CPUs introduces severe systems bottlenecks: context-swapping latency between draft and target graphs, and memory allocation overhead during KV cache rollbacks. We introduce SubTernary, an execution framework that eliminates these co
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
- SPECTRA: Adaptive Execution of Speculative Decoding on a Runtime-Reconfigurable Tiled Architecture#1051246
- SPECTRA: Adaptive Execution of Speculative Decoding on a Runtime-Reconfigurable Tiled Architecture#1028648
- Spexis: Speculative Lookahead Scheduling for LLM Inference#1128643
- Spexis: Speculative Lookahead Scheduling for LLM Inference#1108713
- T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration#1344596
Record · ID 1412912
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