{"id":28319486,"url":"https://github.com/orion-zhen/llm-throughput-eval","last_synced_at":"2026-03-01T12:03:32.593Z","repository":{"id":279910542,"uuid":"869942185","full_name":"Orion-zhen/llm-throughput-eval","owner":"Orion-zhen","description":"evaluate llm's generation speed via API","archived":false,"fork":false,"pushed_at":"2025-05-10T15:05:07.000Z","size":36,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-22T09:38:46.790Z","etag":null,"topics":["llm","llm-evaluation","throughput","throughput-performance"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Orion-zhen.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":"2024-10-09T07:04:57.000Z","updated_at":"2025-05-10T15:05:10.000Z","dependencies_parsed_at":"2025-02-28T13:17:30.805Z","dependency_job_id":"ed74ab2d-2b52-4a93-81db-67ed9ac86bbc","html_url":"https://github.com/Orion-zhen/llm-throughput-eval","commit_stats":null,"previous_names":["orion-zhen/llm-throughput-eval"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Orion-zhen/llm-throughput-eval","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-zhen%2Fllm-throughput-eval","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-zhen%2Fllm-throughput-eval/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-zhen%2Fllm-throughput-eval/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-zhen%2Fllm-throughput-eval/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Orion-zhen","download_url":"https://codeload.github.com/Orion-zhen/llm-throughput-eval/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orion-zhen%2Fllm-throughput-eval/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29969243,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T11:43:06.159Z","status":"ssl_error","status_checked_at":"2026-03-01T11:43:03.887Z","response_time":124,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["llm","llm-evaluation","throughput","throughput-performance"],"created_at":"2025-05-25T09:10:58.213Z","updated_at":"2026-03-01T12:03:32.588Z","avatar_url":"https://github.com/Orion-zhen.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# llm-throughput-eval\n\nEvaluate llm's generation speed via API\n\n## Quick Start\n\n### Get the repository\n\nClone:\n\n```shell\ngit clone https://github.com/Orion-zhen/llm-throughput-eval.git\n```\n\nInstall dependencies:\n\n```shell\npip install -r requirements.txt\n```\n\n### Go\n\n```shell\npython evel.py -m \u003cyour model name\u003e -u \u003ctarget API URL\u003e -n \u003ctotal requests\u003e -c \u003cconcurrencies\u003e -t \u003cAPI token\u003e\n```\n\nExample:\n\n```shell\npython eval.py -m \"qwq:32b\"\n```\n\nThis will send 16 requests with 4 concurrency to local ollama API (should be \u003chttp://127.0.0.1:11434\u003e) with model qwq:32b\n\nFull arguments:\n\n```shell\nusage: eval.py [-h] [--concurrency CONCURRENCY] [--requests REQUESTS] [--url URL] [--model MODEL]\n\nAsync HTTP Benchmark Tool\n\noptions:\n  -h, --help            show this help message and exit\n  --concurrency, -c CONCURRENCY\n                        Maximum concurrent requests.\n  --requests, -n REQUESTS\n                        Total number of requests to send.\n  --url, -u URL         Base URL for the API (e.g., http://localhost:8000). '/v1/chat/completions' will be appended.\n  --model, -m MODEL     Model name to use in the request payload.\n  --token, -t TOKEN     Bearer token for API authentication.\n```\n\n## Credits\n\nThe code is inspired by [this article](https://blog.csdn.net/arkohut/article/details/139076652)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Forion-zhen%2Fllm-throughput-eval","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Forion-zhen%2Fllm-throughput-eval","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Forion-zhen%2Fllm-throughput-eval/lists"}