Filter by

  • Publication Year
  • Availability
  • Attachment
  • Collection Type
    See More
  • General Material Designation
    See More
  • Location
    See More
  • Language
    See More
Found 1 from your keywords: author=Sofhiea, Defhanaya
cover
OPTIMASI KERNEL CUDA BERBASIS MEMORY-AWARE UNTUK SELF-ATTENTION PADA INFERENS…
Comment Share
Sofhiea, Defhanaya

The self-attention mechanism in Large Language Models (LLMs) is computationally intensive and memory-bound, posing significant challenges for inference on consumer-grade hardware. This research proposes a memory-aware optimization of CUDA kernels for the self-attention mechanism within the GPT-2 architecture, integrating Shared Memory Tiling, Streaming Softmax, and Kernel Fusion to minimize glo…

Edition
-
ISBN/ISSN
-
Collation
xviii, 68 hlm.; ilus.; 29 cm
Series Title
-
Call Number
T1955422026