Reading

GPU Forecasters: Predicting GPU Kernel Performance with Large Language Models to Accelerate Optimization

This article introduces the GPU Forecasters method, which uses large language models as selective proxies to predict GPU kernel performance. It can evaluate several times more candidate solutions under the same GPU budget, significantly improving kernel search efficiency.

GPU内核优化大语言模型性能预测强化学习代码优化深度学习系统代理模型编译器优化

Published 2026-05-29 23:56Recent activity 2026-06-01 10:56Estimated read 7 min

GPU Forecasters: Predicting GPU Kernel Performance with Large Language Models to Accelerate Optimization

Section 01

Introduction: GPU Forecasters—Accelerating GPU Kernel Optimization with LLM

This article introduces the GPU Forecasters method published on arXiv on May 29, 2026. Its core is to use large language models (LLM) as selective proxies to predict the relative performance of GPU kernels, reducing reliance on actual hardware measurements. Under the same GPU budget, this method can evaluate several times more candidate solutions, significantly improving kernel search efficiency and aiding deep learning system optimization.

Section 02

Background: Measurement Bottlenecks in GPU Kernel Optimization and Contradictions Brought by LLM

GPU kernels are core workloads in deep learning, and their performance directly determines system efficiency. Existing optimization methods require repeated hardware measurements. Although a single measurement (compilation + execution + synchronization) is short, the total cost of large-scale searches is extremely high. In recent years, LLM's code generation capability has improved, but hardware evaluation has become a bottleneck—they can generate a large number of candidates but lack sufficient GPU time to evaluate them. The core question: Can we use LLM to predict performance and reduce hardware reliance?

Section 03

Method: Selective Proxy Mechanism of GPU Forecasters

The GPU Forecasters framework uses LLM as a selective proxy, which needs to have two characteristics: 1. Accuracy (predicting relative performance); 2. Selectivity (delegating hardware measurement when uncertain). The prediction target is relative performance (whether A is faster than B), which is easier than absolute values and meets search requirements. Proxy evaluation metrics include accuracy, calibration (confidence matches reliability), and utility (finding faster kernels under limited budget).

Section 04

Method: RL Enhancement and Kernel Search Process

The study uses reinforcement learning (RL) to improve proxy performance: penalizing incorrect high-confidence predictions and rewarding correct selectivity. Experiments show that accuracy and calibration are significantly improved after RL training. Steps to integrate into the search process: 1. Generate candidates; 2. Proxy predicts pairwise performance; 3. Accept high-confidence predictions, perform hardware measurement for low-confidence ones; 4. Update search state and repeat until budget is exhausted.

Section 05

Experimental Evidence: Efficiency Improvement and Value of Selective Mechanism

Key findings: LLM's relative performance prediction accuracy exceeds random; RL training further improves it; under the same GPU budget, it can evaluate 3-5 times more candidates, and the best kernel found is 10-20% faster. The selective mechanism is key: no selectivity degrades search quality, and retaining 10-30% of candidates for measurement achieves the best balance.

Section 06

Technical Details: Input Representation and Prediction Head Design

The input needs to include kernel code, hardware specifications, and problem scale; the combination of code and hardware representation yields the best results. Prediction head design: pairwise comparison head (outputs the probability that A is faster than B), ranking head (relative performance score), confidence head (prediction + confidence). Training data comes from historical search logs, synthetic data, and public benchmarks.

Section 07

Practical Recommendations: Steps to Apply GPU Forecasters

Data collection: Record search history, establish benchmark suites, and continuously update data; Proxy deployment: Start with simple pairwise comparisons, then gradually introduce confidence and RL; Integration with search: Dynamically allocate budget, tolerate errors, and update the proxy via online learning.

Section 08

Conclusion: A New Direction for AI-Assisted AI Infrastructure Optimization

GPU Forecasters embodies the recursive value of AI-assisted AI infrastructure optimization—LLMs not only generate code but also understand performance characteristics. In the future, it can be extended to hardware such as TPU/NPU and multi-objective optimization, becoming a key tool for complex system optimization and driving the development of AI from the application layer to the infrastructure layer as an optimization engine.

Continue Reading

Keep going with more reads from the same topic.

Nornir MCP Server: An Enterprise-Grade Bridge for Integrating Large Language Models into Network Automation

Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.

Recent activity 2026-05-06 20:51

Bibliothèque Française LLM: A French Public Domain Literature Index System Optimized for Large Language Models

Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.

Recent activity 2026-05-06 20:50

Splinter: A Lock-Free Zero-Copy Shared Memory KV and Vector Storage Library That Eliminates Socket and Memcpy Overhead for LLM Inference

Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.

Recent activity 2026-04-03 08:49

Folkering OS: When the Operating System Itself Is AI—A Self-Evolving Bare-Metal Rust System

Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.

Recent activity 2026-04-09 16:15