AMD
Corporate • 🇺🇸 United States
Big TechPapers (L12M)
50
Researchers (≈)
111
Papers w/ Code
11
Papers w/ Dataset
0
Topic Overview
Bubble chart placeholder
Recent Papers (see all )
tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection
Distributed, Parallel, and Cluster Computing
Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
Computation and Language
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Computation and Language
Pickle Prefetcher: Programmable and Scalable Last-Level Cache Prefetcher
Hardware Architecture
Iris: First-Class Multi-GPU Programming Experience in Triton
Code
Distributed, Parallel, and Cluster Computing