{"id":22420519,"url":"https://github.com/eniompw/llama-cpp-gpu","last_synced_at":"2026-05-05T04:06:16.360Z","repository":{"id":184466282,"uuid":"657487363","full_name":"eniompw/llama-cpp-gpu","owner":"eniompw","description":"Load larger models by offloading model layers to both GPU and CPU","archived":false,"fork":false,"pushed_at":"2023-07-28T14:00:05.000Z","size":112,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-18T23:15:32.186Z","etag":null,"topics":["colab","colab-notebook","gpu","gpu-acceleration","llama","llama-cpp","llamacpp"],"latest_commit_sha":null,"homepage":"","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/eniompw.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}},"created_at":"2023-06-23T07:05:53.000Z","updated_at":"2023-11-11T16:45:50.000Z","dependencies_parsed_at":"2023-07-28T15:12:10.108Z","dependency_job_id":null,"html_url":"https://github.com/eniompw/llama-cpp-gpu","commit_stats":null,"previous_names":["eniompw/llama-cpp-gpu"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eniompw%2Fllama-cpp-gpu","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eniompw%2Fllama-cpp-gpu/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eniompw%2Fllama-cpp-gpu/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eniompw%2Fllama-cpp-gpu/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eniompw","download_url":"https://codeload.github.com/eniompw/llama-cpp-gpu/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245785715,"owners_count":20671631,"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":["colab","colab-notebook","gpu","gpu-acceleration","llama","llama-cpp","llamacpp"],"created_at":"2024-12-05T16:20:03.972Z","updated_at":"2026-05-05T04:06:16.308Z","avatar_url":"https://github.com/eniompw.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLaMA.cpp GPU\n\nOffloads some of the model layers to the GPU, allowing larger models to be loaded\n\n![model](https://github.com/eniompw/llama-cpp-gpu/blob/main/model-details.png)\n![colab resources](https://github.com/eniompw/llama-cpp-gpu/blob/main/colab-resources.png)\n![parameters](https://github.com/eniompw/llama-cpp-gpu/blob/main/size-parameters.png)\n\n* [cuBLAS](https://github.com/ggerganov/llama.cpp#cublas)\n* [Model](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-GGML#how-to-run-in-llamacpp)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feniompw%2Fllama-cpp-gpu","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feniompw%2Fllama-cpp-gpu","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feniompw%2Fllama-cpp-gpu/lists"}