arXiv (All)
open access
SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving
No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tensor parallelism, many independent requests favor data-parallel attention, and long prompts favor context parallelism. Reasoning, agentic, and RL-rollout workloads make a fixed choice
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
- SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving#1122253
- English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training#1048631
- HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models#822437
- Large Language Models Are Human-Level Prompt Engineers#16578
- Official Review · ICLR 2025#787126
Record · ID 1141940
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