Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

Documenti analoghi

• Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
  di: Maczan, Jędrzej
  Pubblicazione: (2026)
• LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory
  di: Sorensen, Tyler, et al.
  Pubblicazione: (2024)
• Efficient and Portable Support for Overdecomposition on Distributed Memory GPGPU Platforms
  di: Bhosale, Aditya, et al.
  Pubblicazione: (2026)
• KEET: Explaining Performance of GPU Kernels Using LLM Agents
  di: Davis, Joshua H., et al.
  Pubblicazione: (2026)
• Beyond Microservices: Testing Web-Scale RCA Methods on GPU-Driven LLM Workloads
  di: Scheinert, Dominik, et al.
  Pubblicazione: (2026)