PulseAugur
EN
LIVE 02:04:08

MusaCoder framework achieves state-of-the-art in GPU kernel generation

By PulseAugur Editorial · [2 sources] ·

Researchers have developed MusaCoder, a novel framework for generating native GPU kernels, which are essential for efficient low-level code execution. This system employs a full-stack training approach, integrating data synthesis, rejection fine-tuning, and reinforcement learning with a specialized verification environment called MooreEval. MusaCoder introduces several techniques to stabilize the reinforcement learning process, leading to improved correctness and speedup compared to existing models. The framework demonstrates strong performance, with its larger version setting a new state-of-the-art for native GPU kernel generation. AI

IMPACT Establishes a new state-of-the-art in native GPU kernel generation, potentially accelerating AI development on emerging hardware.

RANK_REASON The cluster contains an arXiv paper detailing a new model and training framework for a specific AI task.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

MusaCoder framework achieves state-of-the-art in GPU kernel generation

COVERAGE [2]

  1. arXiv cs.CL TIER_1 English(EN) · Kun Cheng, Songshuo Lu, Sicong Liao, Tankun Li, Yafei Zhang, Dong Yang, Qiheng Lv, Hua Wang, Zhi Chen, Yaohua Tang ·

    MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

    arXiv:2606.04847v1 Announce Type: cross Abstract: Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggle with this task, while execution-based reinforcement learning suffers from spar…

  2. arXiv cs.LG TIER_1 English(EN) · Yaohua Tang ·

    MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU

    Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggle with this task, while execution-based reinforcement learning suffers from sparse rewards, reward hacking, and training instabili…

RELATED ENTITIES

RELATED TOPICS