{"id":30101159,"url":"https://github.com/loreloc/triturus","last_synced_at":"2026-04-17T08:02:02.669Z","repository":{"id":306422616,"uuid":"997904170","full_name":"loreloc/triturus","owner":"loreloc","description":"A bunch of triton kernels with increasing complexity for learning and exploring triton and GPU programming","archived":false,"fork":false,"pushed_at":"2025-08-01T23:20:24.000Z","size":129,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-11T00:03:18.085Z","etag":null,"topics":["cuda","pytorch","triton"],"latest_commit_sha":null,"homepage":"","language":"Python","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/loreloc.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}},"created_at":"2025-06-07T12:50:59.000Z","updated_at":"2025-08-01T23:20:28.000Z","dependencies_parsed_at":"2025-07-25T17:27:02.996Z","dependency_job_id":null,"html_url":"https://github.com/loreloc/triturus","commit_stats":null,"previous_names":["loreloc/triturus"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/loreloc/triturus","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loreloc%2Ftriturus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loreloc%2Ftriturus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loreloc%2Ftriturus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loreloc%2Ftriturus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/loreloc","download_url":"https://codeload.github.com/loreloc/triturus/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/loreloc%2Ftriturus/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31920518,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"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":["cuda","pytorch","triton"],"created_at":"2025-08-09T17:26:41.416Z","updated_at":"2026-04-17T08:02:02.650Z","avatar_url":"https://github.com/loreloc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🦎 Triturus 🦎\n\nThe following table describes the implemented kernels.\n\n| Kernel ID    | Description                                  | Operation                                              | Source                       |\n| ------------ | -------------------------------------------- | ------------------------------------------------------ | ---------------------------- |\n| vadd         | Vector addition                              | $a_i+b_i$                                              | [add](triturus/add.py)       |\n| vamax        | Vector maximum                               | $\\max_i a_i$                                           | [max](triturus/max.py)       |\n| vmax         | Vector maximum with indices                  | $(\\max_i a_i, \\arg\\max_i a_i)$                         | [max](triturus/max.py)       |\n| matmax       | Matrix maximum along one axis                | $\\max_i a_{ij}$ or $\\max_j a_{ij}$                     | [max](triturus/max.py)       |\n| mm           | Matrix multiplication                        | $\\sum_j a_{ij}b_{jk}$                                  | [mm](triturus/mm.py)         |\n| lm2exp       | Batch log-matmul, one matrix in log-space    | $\\log(\\sum_j a_{rij} \\exp b_{rjk})$                    | [lm2exp](triturus/lm2exp.py) |\n| lt2exp       | Batch log-Tucker2, two matrices in log-space | $\\log(\\sum_{i,j} w_{rsij} \\exp a_{rik} \\exp b_{rjk})$  | [lt2exp](triturus/lt2exp.py) |\n\n## Benchmarks Gallery\n\n| Kernel ID    | Benchmark Description                                    | Baselines   | Results                      |\n| ------------ | -------------------------------------------------------- | ----------- | ---------------------------- |\n| vmax         | Vector maximum with and without indices                  | torch       | [here](#benchmark-of-vmax)   |\n| matmax       | Matrix maximum along rows and columns                    | torch       | [here](#benchmark-of-matmax) |\n| mm           | Matrix multiplication with square matrices               | torch       | [here](#benchmark-of-mm)     |\n| lm2exp       | Batch log-matmul, square and rectangular batch matrices  | torch + jit | [here](#benchmark-of-lm2exp) |\n| lt2exp       | Batch log-Tucker2, square and rectangular batch matrices | torch + jit | [here](#benchmark-of-lt2exp) |\n\n---\n\n### Benchmark of vmax\n\n\u003cimg src=\"https://github.com/loreloc/triturus/releases/download/v0.1/benchmark-vmax.png\" alt=\"vmax\" height=256px\u003e\n\n### Benchmark of matmax\n\n\u003cimg src=\"https://github.com/loreloc/triturus/releases/download/v0.1/benchmark-matmax.png\" alt=\"matmax\" height=256px\u003e\n\n### Benchmark of mm\n\n\u003cimg src=\"https://github.com/loreloc/triturus/releases/download/v0.1/benchmark-mm.png\" alt=\"mm\" height=256px\u003e\n\n### Benchmark of lm2exp\n\n\u003cimg src=\"https://github.com/loreloc/triturus/releases/download/v0.1/benchmark-lm2exp.png\" alt=\"lm2exp\" height=256px\u003e\n\n### Benchmark of lt2exp\n\n\u003cimg src=\"https://github.com/loreloc/triturus/releases/download/v0.1/benchmark-lt2exp.png\" alt=\"lt2exp\" height=256px\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floreloc%2Ftriturus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Floreloc%2Ftriturus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Floreloc%2Ftriturus/lists"}