{"id":20185048,"url":"https://github.com/unifyai/aibench-llm-endpoints","last_synced_at":"2025-09-21T18:32:26.274Z","repository":{"id":220986463,"uuid":"751152349","full_name":"unifyai/aibench-llm-endpoints","owner":"unifyai","description":"Runner in charge of collecting metrics from LLM inference endpoints for the Unify Hub","archived":false,"fork":false,"pushed_at":"2024-02-05T15:06:18.000Z","size":10,"stargazers_count":17,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-11-14T03:11:31.995Z","etag":null,"topics":["benchmark","endpoints","llm","llm-inference","python"],"latest_commit_sha":null,"homepage":"https://unify.ai/hub","language":"Python","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/unifyai.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":"2024-02-01T03:00:30.000Z","updated_at":"2024-10-09T08:41:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"9522d254-08b4-4bf2-8417-3e3524754116","html_url":"https://github.com/unifyai/aibench-llm-endpoints","commit_stats":null,"previous_names":["unifyai/aibench-llm-endpoints"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unifyai%2Faibench-llm-endpoints","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unifyai%2Faibench-llm-endpoints/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unifyai%2Faibench-llm-endpoints/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/unifyai%2Faibench-llm-endpoints/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/unifyai","download_url":"https://codeload.github.com/unifyai/aibench-llm-endpoints/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233785224,"owners_count":18729845,"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":["benchmark","endpoints","llm","llm-inference","python"],"created_at":"2024-11-14T03:10:56.873Z","updated_at":"2025-09-21T18:32:21.020Z","avatar_url":"https://github.com/unifyai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AIBench LLM Endpoints\n\n## Overview\nThis code provides a benchmarking runner, `AIBench-LLM`, for evaluating the performance of a large language model (LLM) inference endpoint. The benchmark measures various metrics such as Time to First Token (TTFT), End to End Latency, Inter-Token Latency (ITL), Output Tokens per Second, and more.\n\nThe AIBench Runner is in charge of collecting metrics from LLM inference endpoints for the [Unify Hub](https://unify.ai/hub). More information about the full methodology is available [here 📑](https://unify.ai/docs/hub/concepts/benchmarks.html)\n\nContributions and discussions around the methodology and the runner are definitely welcome, you can join the [Unify Discord](https://discord.com/invite/sXyFF8tDtm) if this sounds interesting!\n\n## Metrics\nThe benchmark runner collects the following metrics:\n\n- `load`: Number of concurrent requests.\n- `input_policy`: Input policy used (short or long).\n- `ttft`: Time-to-first-token for each request.\n- `e2e_latency`: End-to-end latency for each request.\n- `itl`: Inter-token Latency.\n- `cold_start`: Cold start time (if applicable).\n- `prompt_tokens`: Number of tokens in the input prompt.\n- `output_tokens`: Number of tokens in the LLM output.\n- `total_tokens`: Total number of tokens (input + output).\n- `output_tks_per_sec`: Output tokens per second.\n- `failed_queries`: Number of failed queries.\n\n## Usage and Examples\nTo be added this week!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funifyai%2Faibench-llm-endpoints","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funifyai%2Faibench-llm-endpoints","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funifyai%2Faibench-llm-endpoints/lists"}