We introduce OSVBench, a new benchmark for evaluating Large Language Models (LLMs) in generating complete specification code pertaining to operating system kernel verification tasks. The benchmark ...
The overwhelming contributor to energy consumption in AI processors is not arithmetic; it’s the movement of data.
OS-R1 is an agentic Linux kernel tuning framework that leverages reinforcement learning (RL) and large language models (LLMs) for efficient kernel configuration. It introduces a rule-based RL approach ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback