AI Infra Wiki

标签: cxl

此标签下有4条笔记。

  • 2026年9月18日

    CXL Tiered Memory

    • cxl
    • memory
    • memory-bandwidth
    • interconnect
    • fabric
    • storage
    • infrastructure
    • latency
  • 2026年9月14日

    Composable CXL Memory as K8s Shared Memory for LLM Serving

    • cxl
    • memory
    • kv-cache
    • serving
    • inference
    • fabric
    • disaggregated-inference
    • latency
    • serving-system
  • 2026年9月03日

    DynaNDE: Dynamic Near-Data Expert Scheduling for Batched MoE Inference

    • moe
    • inference
    • cxl
    • scheduling
    • memory
    • accelerator
    • llm
    • throughput
    • interconnect
    • batching
    • expert-parallelism
    • serving
    • architecture
  • 2026年8月26日

    Hot Chips 2026: NVIDIA Vera CPU

    • nvidia
    • cpu
    • scale-up
    • cxl
    • memory
    • inference
    • rack
    • interconnect
    • architecture
    • agentic-ai
    • memory-bandwidth

Created with Quartz v4.5.1 © 2026

  • Source Wiki
  • Quartz