Amoeba: Runtime Tensor Parallel Transformation for LLM Inference Services

Documenti analoghi

• AnchorTP: Resilient LLM Inference with State-Preserving Elastic Tensor Parallelism
  di: Xu, Wendong, et al.
  Pubblicazione: (2025)
• SeaLLM: Service-Aware and Latency-Optimized Resource Sharing for Large Language Model Inference
  di: Zhao, Yihao, et al.
  Pubblicazione: (2025)
• Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism
  di: Srivatsa, Vikranth, et al.
  Pubblicazione: (2026)
• LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling
  di: Da, Wei, et al.
  Pubblicazione: (2026)
• Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference
  di: Shyam, Vasu, et al.
  Pubblicazione: (2026)