{"id":26103492,"url":"https://github.com/inftyai/puma","last_synced_at":"2025-03-09T20:07:14.369Z","repository":{"id":276820997,"uuid":"857647040","full_name":"InftyAI/PUMA","owner":"InftyAI","description":"Aim to be a lightweight, high-performance inference engine for heterogeneous devices. WIP.","archived":false,"fork":false,"pushed_at":"2025-02-25T08:28:50.000Z","size":45,"stargazers_count":0,"open_issues_count":4,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-04T16:15:25.977Z","etag":null,"topics":["llm","llm-inference","rust"],"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/InftyAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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}},"created_at":"2024-09-15T08:12:38.000Z","updated_at":"2025-02-25T08:28:54.000Z","dependencies_parsed_at":"2025-02-25T07:33:19.630Z","dependency_job_id":null,"html_url":"https://github.com/InftyAI/PUMA","commit_stats":null,"previous_names":["inftyai/puma"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InftyAI%2FPUMA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InftyAI%2FPUMA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InftyAI%2FPUMA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/InftyAI%2FPUMA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/InftyAI","download_url":"https://codeload.github.com/InftyAI/PUMA/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242744089,"owners_count":20178174,"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":["llm","llm-inference","rust"],"created_at":"2025-03-09T20:07:13.608Z","updated_at":"2025-03-09T20:07:14.320Z","avatar_url":"https://github.com/InftyAI.png","language":"Rust","readme":"# PUMA\n\nPuma aims to be a lightweight, high-performance inference engine for heterogeneous devices. *Currently under active development.*\n\n## How to Run\n\n### Build\n\nRun `make build` to build the **puma** binary.\n\n### Run\n\nRun `./puma help` to see all available commands.\n\nFor example, you can run `./puma version` to see the binary version.\n\n## Supported Backends\n\nUse [llama.cpp](https://github.com/ggerganov/llama.cpp) as the default backend for quick prototyping, will implement our own backend in the future.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finftyai%2Fpuma","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finftyai%2Fpuma","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finftyai%2Fpuma/lists"}