RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

• URL: http://arxiv.org/abs/2608.12004v1
• Date: Wed, 12 Aug 2026 12:38:17 GMT
• Title: RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
• Abstract summary: We introduce RealisticTritonBench, the first benchmark to derive Triton kernel generation tasks from real-world pull requests in popular AI frameworks.<n> RealisticTritonBench integrates PRs that modify Triton kernels from popular open-source AI frameworks and transforms them into generation tasks with concrete engineering contexts.<n>We evaluate leading LLMs on RealisticTritonBench and find that they still struggle with real-world Triton kernel generation tasks.
• Score: 7.371299443009948
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU kernels. Recent advances show the potential of large language models (LLMs) to automatically generate Triton kernels, reducing the manual effort required from expert kernel developers. Several benchmarks evaluate LLM-generated Triton kernels. However, they suffer from three key limitations: (1) they restrict tasks to PyTorch-to-Triton translation, failing to reflect the diversity and complexity of real-world Triton tasks; (2) they evaluate only individual-kernel performance rather than end-to-end performance, the core criterion for real-world deployment in AI frameworks; and (3) they rely on manually written evaluation scripts for individual kernels, which may contain flaws that models can exploit to bypass correctness checks and obtain inflated scores. To address these limitations, we introduce RealisticTritonBench, the first benchmark to derive Triton kernel generation tasks from real-world pull requests in popular AI frameworks, enabling realistic, production-like evaluation. RealisticTritonBench systematically extracts PRs that modify Triton kernels from popular open-source AI frameworks and transforms them into generation tasks with concrete engineering contexts. Each task takes a natural language requirement as input and requires a corresponding Triton kernel implementation, with a complete and reproducible evaluation environment. Unlike prior benchmarks focused on isolated kernel performance, RealisticTritonBench integrates generated kernels into their original frameworks and evaluates them using end-to-end tests, enabling a more faithful assessment. We evaluate leading LLMs on RealisticTritonBench and find that they still struggle with real-world Triton kernel generation tasks.

Related papers

• Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis [68.7701048879757]
  EvoKernel is a self-evolving agentic framework that automates the lifecycle of kernel synthesis.<n>It learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective.<n>It improves models' correctness from 11.0% to 83.0% and a median speedup of 3.60x over initial drafts.
  arXiv  Detail & Related papers  (2026-03-11T14:57:06Z)
• RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation [76.22852262683746]
  We introduce RADAR, a benchmark designed to systematically evaluate VLA generalization under realistic conditions.<n>We apply RADAR to audit multiple state-of-the-art VLA models and uncover severe fragility beneath their apparent competence.
  arXiv  Detail & Related papers  (2026-02-11T16:08:30Z)
• TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization [24.065109818256605]
  TritonForge is a profiling-guided framework for automated GPU kernel optimization.<n>It integrates kernel analysis, runtime profiling, and iterative code transformation to streamline the process.<n>It achieves up to 5x performance improvement over baseline implementations and on average 1.76x of the cases are successful.
  arXiv  Detail & Related papers  (2025-12-09T23:44:35Z)
• Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation [52.11339614452127]
  Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions.<n>Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities.<n>We propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner.
  arXiv  Detail & Related papers  (2025-11-18T04:32:00Z)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• TritonRL: Training LLMs to Think and Code Triton Without Cheating [14.859089778654933]
  TritonRL is trained with a novel training framework that enables robust and automated kernel synthesis.<n>Our experiments on KernelBench demonstrate that TritonRL achieves state-of-the-art correctness and speedup, surpassing all other Triton-specific models.
  arXiv  Detail & Related papers  (2025-10-18T21:36:10Z)
• Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks [11.253534066141668]
  It is imperative to automate low-level kernel development to meet performance and productivity demands.<n>Major cloud providers, semiconductor companies, and research institutions are now investing heavily in AI-driven code generation for GPU.<n>We present an evaluation suite for Triton-based GPU kernels and GEAK (Generating Efficient AI-centric GPU Kernels)
  arXiv  Detail & Related papers  (2025-07-31T02:26:58Z)
• AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs [87.8306870967343]
  We introduce AutoTriton, the first model dedicated to Triton programming powered by reinforcement learning (RL)<n>AutoTriton performs supervised fine-tuning (SFT) to be equipped with essential Triton programming expertise using a high-quality data gathering pipeline.<n> Experiments across five evaluation channels of TritonBench and KernelBench illustrate that our 8B model AutoTriton achieves performance comparable to mainstream large models.
  arXiv  Detail & Related papers  (2025-07-08T05:38:24Z)
• TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators [59.625889531331815]
  Triton is a high-level Python-like language designed for building efficient GPU kernels.<n>Despite advances in large language models (LLMs) for conventional code generation, these models struggle to generate accurate, performance-optimized Triton code.<n>In this work, we introduce TritonBench, the first comprehensive benchmark for Triton operator generation.
  arXiv  Detail & Related papers  (2025-02-20T17:21:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.