Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers

Documenti analoghi

• Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU
  di: Levine, Reese, et al.
  Pubblicazione: (2026)
• Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
  di: Li, Zhuojin, et al.
  Pubblicazione: (2025)
• TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
  di: Vellaisamy, Prabhu, et al.
  Pubblicazione: (2026)
• LEO: Tracing GPU Stall Root Causes via Cross-Vendor Backward Slicing
  di: Xia, Yuning, et al.
  Pubblicazione: (2026)
• GPU Cluster Scheduling for Network-Sensitive Deep Learning
  di: Sharma, Aakash, et al.
  Pubblicazione: (2024)