Documenti analoghi

• RAPID-LLM: Resilience-Aware Performance analysis of Infrastructure for Distributed LLM Training and Inference
  di: Karfakis, George, et al.
  Pubblicazione: (2025)
• Fault-Tolerant Hybrid-Parallel Training at Scale with Reliable and Efficient In-memory Checkpointing
  di: Wang, Yuxin, et al.
  Pubblicazione: (2023)
• Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
  di: Yuan, Ziqi, et al.
  Pubblicazione: (2025)
• Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms
  di: Zhang, Yaozheng, et al.
  Pubblicazione: (2025)
• HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
  di: Lin, Mao, et al.
  Pubblicazione: (2026)