AscendGYM benchmark targets cost-aware kernel optimization on Ascend NPUs
This story is from 2026-11-17. It is preserved in the archive; the latest stories are on the live feed.
A new arXiv paper introduces AscendGYM, a benchmark for cost-aware kernel optimization on Ascend NPUs, aimed at improving LLM training and inference efficiency where existing Ascend kernel benchmarks fall short.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv cs.AI
AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs