{"id":47758098,"url":"https://github.com/internlm/kernel-smith","last_synced_at":"2026-04-06T07:01:09.315Z","repository":{"id":348166688,"uuid":"1195949433","full_name":"InternLM/Kernel-Smith","owner":"InternLM","description":null,"archived":false,"fork":false,"pushed_at":"2026-03-31T03:23:03.000Z","size":1094,"stargazers_count":14,"open_issues_count":1,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-04-05T06:02:51.488Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/InternLM.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"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":"2026-03-30T08:14:48.000Z","updated_at":"2026-04-05T04:51:42.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/InternLM/Kernel-Smith","commit_stats":null,"previous_names":["internlm/kernel-smith"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/InternLM/Kernel-Smith","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternLM%2FKernel-Smith","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternLM%2FKernel-Smith/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternLM%2FKernel-Smith/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternLM%2FKernel-Smith/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/InternLM","download_url":"https://codeload.github.com/InternLM/Kernel-Smith/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InternLM%2FKernel-Smith/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31463015,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-05T21:22:52.476Z","status":"online","status_checked_at":"2026-04-06T02:00:07.287Z","response_time":112,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2026-04-03T04:53:43.288Z","updated_at":"2026-04-06T07:01:09.292Z","avatar_url":"https://github.com/InternLM.png","language":null,"readme":"# Kernel-Smith\n\n**Kernel-Smith** is a GPU kernel generation system developed by the Shanghai Artificial Intelligence Laboratory and MetaX. The technical report is available [here](https://arxiv.org/pdf/2603.28342).\n\n\u003e We do not currently plan to release the Kernel-Smith model weights or agent code. For now, this repository will focus on sharing generated kernels, benchmarks, and related documentation. Stay tuned.\n\n## 🌟 Highlights\n\n- Uses an evolution-based optimization loop with stable evaluation on both **NVIDIA Triton** and **MetaX MACA** backends.\n- Trains for kernel improvement by rewarding correctness-preserving changes that increase performance.\n- Outperforms frontier models like Gemini-3.0-pro and Claude-4.6-opus on KernelBench.\n\n## 🚀 Production-Level Deployment\n\nKernel-Smith generated kernels have already been integrated into several open-source projects:\n\n| Project | Optimized Kernel | Impact | Pull Request |\n| :--- | :--- | :--- | :--- |\n| **SGLang** | `normal_decode_set_metadata` | **4.78x** kernel acceleration | [#20778](https://github.com/sgl-project/sglang/pull/20778) |\n| **LMDeploy** | DeepSeek MoE Routing | **1.36x** kernel acceleration | [#4345](https://github.com/InternLM/lmdeploy/pull/4345) |\n| **DLBlas** | DeepSeek Engram kernels | Accelerated architecture research | [#102](https://github.com/DeepLink-org/DLBlas/pull/102) |\n\n## 🌐 Try It Out\n\n[Kernel-Smith Online Demo](https://chat.intern-ai.org.cn/kernel-smith)","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finternlm%2Fkernel-smith","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finternlm%2Fkernel-smith","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finternlm%2Fkernel-smith/lists"}