Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended

Documenti analoghi

• POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
  di: Kamath, Aditya K, et al.
  Pubblicazione: (2024)
• Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
  di: Jo, Myeong Jun
  Pubblicazione: (2026)
• Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks
  di: Topcu, Burak, et al.
  Pubblicazione: (2026)
• MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices
  di: Shakerdargah, Mohammadali, et al.
  Pubblicazione: (2024)
• Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models
  di: Lo, Yun-Chen, et al.
  Pubblicazione: (2024)