# QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation

arXiv: https://arxiv.org/abs/2511.20100 · HTML: https://mlsanity.com/paper/2511.20100/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 18 of its 47 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators](https://mlsanity.com/paper/2502.14752/) (2025)
- [True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning](https://mlsanity.com/paper/2401.14151/) (2024)
- [Operator Fusion in XLA: Analysis and Evaluation](https://mlsanity.com/paper/2301.13062/) (2023)
- [QiMeng-TensorOp: Automatically Generating High-Performance Tensor Operators with Hardware Primitives](https://mlsanity.com/paper/2505.06302/) (2025)
- [QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach](https://mlsanity.com/paper/2505.02146/) (2025)
- [QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm](https://mlsanity.com/paper/2506.12355/) (2025)

## Built on by (most cited first, 19 of 19)

- [KernelFoundry: Hardware-aware evolutionary GPU kernel optimization](https://mlsanity.com/paper/2603.12440/) (2026)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization](https://mlsanity.com/paper/2603.10085/) (2026)
- [AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis](https://mlsanity.com/paper/2512.23424/) (2025)
- [AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation](https://mlsanity.com/paper/2601.22760/) (2026)
- [StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning](https://mlsanity.com/paper/2603.02637/) (2026)
- [Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis](https://mlsanity.com/paper/2603.10846/) (2026)
- [FastKernels: Benchmarking GPU Kernel Generation in Production](https://mlsanity.com/paper/2605.23215/) (2026)
- [AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents](https://mlsanity.com/paper/2605.16819/) (2026)
- [MusaCoder: Native GPU Kernel Generation with Full-Stack Training on Moore Threads GPU](https://mlsanity.com/paper/2606.04847/) (2026)
- [RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks](https://mlsanity.com/paper/2608.12004/) (2026)
- [Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation](https://mlsanity.com/paper/2602.07670/) (2026)
- [Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages](https://mlsanity.com/paper/2605.28213/) (2026)
- [SparseDitto: An Agentic Sparse Compilation Framework through Architecture-Aware Synthesis on GPUs](https://mlsanity.com/paper/2608.05033/) (2026)
- [Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory](https://mlsanity.com/paper/2608.25570/) (2026)
- [CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language](https://mlsanity.com/paper/2609.00058/) (2026)
- [KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation](https://mlsanity.com/paper/2609.33074/) (2026)
- [From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis](https://mlsanity.com/paper/2609.35568/) (2026)
- [D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?](https://mlsanity.com/paper/2610.03226/) (2026)

## Abstract (arXiv)

Developing high-performance GPU kernels is critical for AI and scientific computing, but remains challenging due to its reliance on expert crafting and poor portability. While LLMs offer promise for automation, both general-purpose and finetuned LLMs suffer from two fundamental and conflicting limitations: correctness and efficiency. The key reason is that existing LLM-based approaches directly generate the entire optimized low-level programs, requiring exploration of an extremely vast space encompassing both optimization policies and implementation codes. To address the challenge of exploring an intractable space, we propose Macro Thinking Micro Coding (MTMC), a hierarchical framework inspired by the staged optimization strategy of human experts. It decouples optimization strategy from implementation details, ensuring efficiency through high-level strategy and correctness through low-level implementation. Specifically, Macro Thinking employs reinforcement learning to guide lightweight LLMs in efficiently exploring and learning semantic optimization strategies that maximize hardware utilization. Micro Coding leverages general-purpose LLMs to incrementally implement the stepwise optimization proposals from Macro Thinking, avoiding full-kernel generation errors. Together, they effectively navigate the vast optimization space and intricate implementation details, enabling LLMs for high-performance GPU kernel generation. Comprehensive results on widely adopted benchmarks demonstrate the superior performance of MTMC on GPU kernel generation in both accuracy and running time. On KernelBench, MTMC achieves near 100% and 70% accuracy at Levels 1-2 and 3, over 50% than SOTA general-purpose and domain-finetuned LLMs, with up to 7.3x speedup over LLMs, and 2.2x over expert-optimized PyTorch Eager kernels. On the more challenging TritonBench, MTMC attains up to 59.64% accuracy and 34x speedup.