{"id":27629552,"url":"https://github.com/bjodah/llm-multi-backend-container","last_synced_at":"2025-04-23T15:26:48.806Z","repository":{"id":284785408,"uuid":"955818219","full_name":"bjodah/llm-multi-backend-container","owner":"bjodah","description":"Docker/podman container for llama.cpp/vllm/exllamav2 orchestrated using llama-swap","archived":false,"fork":false,"pushed_at":"2025-04-15T14:33:59.000Z","size":17,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-15T15:39:24.123Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bjodah.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}},"created_at":"2025-03-27T08:46:49.000Z","updated_at":"2025-04-15T14:34:03.000Z","dependencies_parsed_at":"2025-03-27T17:32:33.730Z","dependency_job_id":"dd9e4853-61e8-4c2c-99ef-b7eb49f55afc","html_url":"https://github.com/bjodah/llm-multi-backend-container","commit_stats":null,"previous_names":["bjodah/llm-multi-backend-container"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjodah%2Fllm-multi-backend-container","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjodah%2Fllm-multi-backend-container/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjodah%2Fllm-multi-backend-container/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bjodah%2Fllm-multi-backend-container/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bjodah","download_url":"https://codeload.github.com/bjodah/llm-multi-backend-container/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250459107,"owners_count":21434024,"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":"2025-04-23T15:26:48.103Z","updated_at":"2025-04-23T15:26:48.786Z","avatar_url":"https://github.com/bjodah.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# llm-multi-backend-container\nUse llama-swap inside a container with vllm, llama.cpp, and exllamav2+tabbyAPI.\n\n## Usage\n```console\n$ head ./bin/host-llm-multi-backend-container.sh\n$ ./bin/host-llm-multi-backend-container.sh --build --force-recreate\n```\n\n## Useful(?) tools\n```console\n$ ./bin/prompt-llm-multi-backend.py stream --model llamacpp-gemma-3-27b-it -t \"Write a poem about a\nbear on a unicycle\" --\n```\n\n## Testing\n```console\n$ bash -x scripts/test-chat-completions.sh\n```\n\n## Notes\n- Right now the config for vLLM struggle with allocating VRAM. Unclear why that is.\n- For customization, you might want to grep for a few keywords:\n```console\n$ git grep 8686\n$ git grep sk-empty\n```\n- Does not seem like `seed` is working?\n```console\n./bin/prompt-llm-multi-backend.py stream -t \"write a poem about a bear on a unicycle\" --opts 'temperature=2.0;max_tokens=1000;seed=42'\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjodah%2Fllm-multi-backend-container","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbjodah%2Fllm-multi-backend-container","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbjodah%2Fllm-multi-backend-container/lists"}