K

Kernelllm GGUF

Developed by lmstudio-community
KernelLLM is a model fine-tuned based on Llama 3.1 Instruct, specifically designed for writing GPU kernels using Triton.
Downloads 214
Release Time : 5/19/2025

Model Overview

This model can convert PyTorch modules into Triton kernels and has been evaluated on the KernelBench-Triton dataset, demonstrating competitive or superior performance.

Model Features

128k tokens context length
Supports ultra-long context, suitable for handling complex kernel generation tasks
GPU kernel code generation
Specially optimized for converting PyTorch modules into efficient Triton GPU kernels
High efficiency
Demonstrates competitive or superior performance in kernel generation tasks compared to larger models

Model Capabilities

Text generation
Code generation
GPU kernel optimization

Use Cases

GPU programming
PyTorch to Triton conversion
Automatically converts PyTorch modules into efficient Triton GPU kernels
Generated kernels can rival hand-optimized code in performance
High-performance computing
Generates optimized GPU kernels for scientific computing and machine learning tasks
Improves execution efficiency for compute-intensive tasks
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase