{"id":28581073,"url":"https://github.com/dimforge/wgml","last_synced_at":"2025-06-11T04:15:37.983Z","repository":{"id":282591730,"uuid":"949062230","full_name":"dimforge/wgml","owner":"dimforge","description":"Cross-platform GPU LLM inference with WebGPU and wgmath.","archived":false,"fork":false,"pushed_at":"2025-05-04T20:19:40.000Z","size":275,"stargazers_count":7,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-09T20:47:47.999Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Rust","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/dimforge.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE-APACHE.txt","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":"2025-03-15T15:35:36.000Z","updated_at":"2025-05-16T21:42:31.000Z","dependencies_parsed_at":"2025-03-15T17:22:30.527Z","dependency_job_id":"96540bd7-0652-4771-a70f-288025219414","html_url":"https://github.com/dimforge/wgml","commit_stats":null,"previous_names":["dimforge/wgml"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dimforge%2Fwgml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dimforge%2Fwgml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dimforge%2Fwgml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dimforge%2Fwgml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dimforge","download_url":"https://codeload.github.com/dimforge/wgml/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dimforge%2Fwgml/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259197999,"owners_count":22820154,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":"2025-06-11T04:15:33.947Z","updated_at":"2025-06-11T04:15:37.972Z","avatar_url":"https://github.com/dimforge.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# wgml − GPU local inference every platform\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./crates/wgml-chat/assets/wgml logo.png\" alt=\"crates.io\" height=\"200px\"\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://discord.gg/vt9DJSW\"\u003e\n        \u003cimg src=\"https://img.shields.io/discord/507548572338880513.svg?logo=discord\u0026colorB=7289DA\"\u003e\n    \u003c/a\u003e\n\u003c/p\u003e\n\n-----\n\n**wgml** is a set of [Rust](https://www.rust-lang.org/) libraries exposing [WebGPU](https://www.w3.org/TR/WGSL/) shaders\nand kernels for local Large Language Models (LLMs) inference on the GPU. It is cross-platform and runs on the web.\n**wgml** can be used as a rust library to assemble your own transformer from the provided operators (and write your\nowns on top of it).\n\nAside from the library, two binary crates are provided:\n- **wgml-bench** is a basic benchmarking utility for measuring calculation times for matrix multiplication with various\n  quantization formats.\n- **wgml-chat** is a basic chat GUI application for loading GGUF files and chat with the model. It can be run natively\n  or on the browser. Check out its [README](./crates/wgml-chat/README.md) for details on how to run it. You can run\n  it from your browser with the [online demo](https://wgmath.rs/demos/wgml/index.html).\n\n⚠️ **wgml** is still under heavy development and might be lacking some important features. Contributions  are welcome!\n\n----","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdimforge%2Fwgml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdimforge%2Fwgml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdimforge%2Fwgml/lists"}