tool · first seen 9 Oct 2026
CUDA graph
NVIDIA mechanism that records and replays a sequence of GPU operations to reduce launch overhead.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Taking Tokenization off the Host for Agentic LLM ServingPapers · 9 Oct 2026 · Mohammad Siavashi, Pascal Schwinte, Ali Banaei, Gerald Q. Maguire, Marco Chiesa,…
- Where Is VLA Inference Time Spent? Bottlenecks and Optimization Interactions Across GPUsPapers · 4 Nov 2026 · Muhammad Danish Waseem, Ahmed Ali-Eldin Hassan
- Read Once, Answer Many: Parallel Prompting for Shared-Context LLM InferencePapers · 11 Nov 2026 · Zekun Zhao, Jeffrey Flanigan
- GC-MoE on SM120: Overlapping Expert-Parallel Token Dispatch with Warp-Level FP8xFP4 Block-Scaled MMA on Consumer BlackwellPapers · 12 Nov 2026 · Yong Li, Haoyu Wang, Kan Liu, Tao Lan
Latest sources
- GC-MoE on SM120: Overlapping Expert-Parallel Token Dispatch with Warp-Level FP8xFP4 Block-Scaled MMA on Consumer BlackwellPapers · 12 Nov 2026 · Yong Li, Haoyu Wang, Kan Liu, Tao Lan
- Read Once, Answer Many: Parallel Prompting for Shared-Context LLM InferencePapers · 11 Nov 2026 · Zekun Zhao, Jeffrey Flanigan
- Where Is VLA Inference Time Spent? Bottlenecks and Optimization Interactions Across GPUsPapers · 4 Nov 2026 · Muhammad Danish Waseem, Ahmed Ali-Eldin Hassan
- Taking Tokenization off the Host for Agentic LLM ServingPapers · 9 Oct 2026 · Mohammad Siavashi, Pascal Schwinte, Ali Banaei, Gerald Q. Maguire, Marco Chiesa,…