{"id":49887877,"url":"https://github.com/amd-agi/neurips2025-gpu-kernels-tutorial","last_synced_at":"2026-05-15T19:05:26.444Z","repository":{"id":357203027,"uuid":"1103326708","full_name":"AMD-AGI/Neurips2025-GPU-kernels-Tutorial","owner":"AMD-AGI","description":"Repo containing artifacts for Neurips 2025 tutorial- How to Build Agents to Generate Kernels for Faster LLMs (and Other Models!)","archived":false,"fork":false,"pushed_at":"2026-05-11T18:49:29.000Z","size":7117,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-11T20:36:38.919Z","etag":null,"topics":["gpu-kernels","kernel-optimization","llamas"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AMD-AGI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-11-24T18:13:15.000Z","updated_at":"2026-05-11T18:36:50.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/AMD-AGI/Neurips2025-GPU-kernels-Tutorial","commit_stats":null,"previous_names":["amd-agi/neurips2025-gpu-kernels-tutorial"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/AMD-AGI/Neurips2025-GPU-kernels-Tutorial","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AMD-AGI%2FNeurips2025-GPU-kernels-Tutorial","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AMD-AGI%2FNeurips2025-GPU-kernels-Tutorial/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AMD-AGI%2FNeurips2025-GPU-kernels-Tutorial/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AMD-AGI%2FNeurips2025-GPU-kernels-Tutorial/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AMD-AGI","download_url":"https://codeload.github.com/AMD-AGI/Neurips2025-GPU-kernels-Tutorial/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AMD-AGI%2FNeurips2025-GPU-kernels-Tutorial/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33075275,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-15T11:35:32.926Z","status":"ssl_error","status_checked_at":"2026-05-15T11:35:31.362Z","response_time":103,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gpu-kernels","kernel-optimization","llamas"],"created_at":"2026-05-15T19:05:19.634Z","updated_at":"2026-05-15T19:05:26.438Z","avatar_url":"https://github.com/AMD-AGI.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NeurIPS 2025 GPU Kernels Tutorial\n\nTutorial materials and hands-on exercises for GPU kernel optimization on GPUs using HIP, Triton, and AI-assisted optimization techniques.\n\n## Overview\n\nThis repository contains comprehensive materials for learning GPU kernel optimization, including:\n- Low-level HIP/C++ implementations demonstrating optimization techniques\n- High-level Triton kernel development tutorials\n- AI-powered kernel optimization using GEAK (GPU Kernel Optimization Agent)\n\n## Contents\n\n### HIP Examples (`src/hip/`)\nC++ kernel implementations with naive and optimized versions:\n- **01-memory-coalescing**: Optimizing memory access patterns\n- **02-loop-unrolling**: A comparison case using unrolling. \n- **Hands_On_Kernels_and_Optmiztion.ipynb**: Interactive tutorial notebook\n\n### Triton Examples (`src/triton/`)\nPython-based kernel optimization tutorials:\n- Fused softmax implementation\n- Layer normalization kernels\n- Comprehensive Triton optimization guide\n\n### GEAK (`src/geak/`)\nAgent-based kernel optimization framework for automated kernel tuning and optimization.\n\n### Tutorial Materials\n- `Neurips_tutorial.pdf`: Complete tutorial documentation\n- `Neurips_tutorial.pptx`: Presentation slides\n\n## Quick Start\n\n1. **HIP Examples**: Navigate to `src/hip/` and compile the C++ files using ROCm toolchain\n2. **Triton Examples**: Open the Jupyter notebooks in `src/triton/` (requires Triton installation)\n3. **GEAK**: Start with `src/geak/Main.ipynb` for agent-based optimization\n\n## Requirements\n\n- ROCm toolkit (for HIP examples)\n- Python with Jupyter (for Triton and GEAK examples)\n- AMD GPU with ROCm support\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famd-agi%2Fneurips2025-gpu-kernels-tutorial","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famd-agi%2Fneurips2025-gpu-kernels-tutorial","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famd-agi%2Fneurips2025-gpu-kernels-tutorial/lists"}