PulseAugur
EN
LIVE 16:13:51

New method uses world models to speed up tensor program optimization

By PulseAugur Editorial · [2 sources] ·

Researchers have developed a novel approach to optimize tensor programs for machine learning systems by modeling schedule evaluation as latent dynamics. This method, inspired by world models, uses a lightweight transition model to predict program states in a continuous latent space, avoiding costly code mutations and encodings. When implemented in TVM AutoScheduler, it significantly improved subgraph latency on GPUs and CPUs and accelerated full-model inference compared to existing methods, all within a reduced measurement budget. AI

IMPACT This research could lead to more efficient AI model training and inference by optimizing the underlying tensor computations.

RANK_REASON The cluster contains an academic paper detailing a new research methodology.

Read on arXiv cs.LG →

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

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Haolin Pan, Lianghong Huang, Xvlin Zhou, Mingjie Xing, Yanjun Wu ·

    Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search

    arXiv:2606.09312v1 Announce Type: new Abstract: Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurement cost with learned cost models, yet they usually evaluate each candidate as a…

  2. arXiv cs.LG TIER_1 English(EN) · Yanjun Wu ·

    Toward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search

    Tensor program optimization is essential for modern machine learning systems, but its search space is enormous. Existing auto-schedulers reduce measurement cost with learned cost models, yet they usually evaluate each candidate as a static code snapshot, ignoring the schedule tra…

RELATED ENTITIES

RELATED TOPICS