Similar Items: Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
- KEET: Explaining Performance of GPU Kernels Using LLM Agents
- On Similarity of Computational Kernels in our Codes and Proxies
- CCL-Bench 1.0: A Trace-Based Benchmark for LLM Infrastructure
- Lifting to tensors when compiling scientific computing workloads for AI Engines
- LLM-Enhanced Deep Reinforcement Learning for Task Offloading in Collaborative Edge Computing
- Agentic Performance at the Edge: Insights from Benchmarking