Signal Detail
This is a raw crawl record from GitHub, currently mapped to #11 on the Newcomers board.
Record Summary
Reproducible LLM inference optimization lab for comparing backends, quantization, latency, VRAM, and output sanity on local hardware. Current movement: NEW. Note: "First time on the board".
This is the name captured in the original signal at crawl time.
The system default name is still in use.
The system default website is still in use.
The system default category is still in use.
Reproducible LLM inference optimization lab for comparing backends, quantization, latency, VRAM, and output sanity on local hardware.
Reproducible LLM inference optimization lab for comparing backends, quantization, latency, VRAM, and output sanity on local hardware. - Happynood/llm-inference-benchmark
Raw Payload
{
"entity_key": "name:llminferencebenchmark",
"source_count": 1,
"providers": [
{
"provider_name": "github",
"slug": "github-Happynood-llm-inference-benchmark",
"external_id": "1268532560",
"external_url": "https://github.com/Happynood/llm-inference-benchmark",
"metric_value": 227,
"payload": {
"id": 1268532560,
"node_id": "R_kgDOS5xFUA",
"name": "llm-inference-benchmark",
"full_name": "Happynood/llm-inference-benchmark",
"private": false,
"owner": {
"login": "Happynood",
"id": 48549027,
"node_id": "MDQ6VXNlcjQ4NTQ5MDI3",
"avatar_url": "https://avatars.githubusercontent.com/u/48549027?v=4",
"gravatar_id": "",
"url": "https://api.github.com/users/Happynood",
"html_url": "https://github.com/Happynood",
"followers_url": "https://api.github.com/users/Happynood/followers",
"following_url": "https://api.github.com/users/Happynood/following{/other_user}",
"gists_url": "https://api.github.com/users/Happynood/gists{/gist_id}",
"starred_url": "https://api.github.com/users/Happynood/starred{/owner}{/repo}",
"subscriptions_url": "https://api.github.com/users/Happynood/subscriptions",
"organizations_url": "https://api.github.com/users/Happynood/orgs",
"repos_url": "https://api.github.com/users/Happynood/repos",
"events_url": "https://api.github.com/users/Happynood/events{/privacy}",
"received_events_url": "https://api.github.com/users/Happynood/received_events",
"type": "User",
"user_view_type": "public",
"site_admin": false
},
"html_url": "https://github.com/Happynood/llm-inference-benchmark",
"description": "Reproducible LLM inference optimization lab for comparing backends, quantization, latency, VRAM, and output sanity on local hardware.",
"fork": false,
"url": "https://api.github.com/repos/Happynood/llm-inference-benchmark",
"forks_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/forks",
"keys_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/keys{/key_id}",
"collaborators_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/collaborators{/collaborator}",
"teams_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/teams",
"hooks_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/hooks",
"issue_events_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/issues/events{/number}",
"events_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/events",
"assignees_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/assignees{/user}",
"branches_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/branches{/branch}",
"tags_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/tags",
"blobs_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/git/blobs{/sha}",
"git_tags_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/git/tags{/sha}",
"git_refs_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/git/refs{/sha}",
"trees_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/git/trees{/sha}",
"statuses_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/statuses/{sha}",
"languages_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/languages",
"stargazers_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/stargazers",
"contributors_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/contributors",
"subscribers_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/subscribers",
"subscription_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/subscription",
"commits_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/commits{/sha}",
"git_commits_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/git/commits{/sha}",
"comments_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/comments{/number}",
"issue_comment_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/issues/comments{/number}",
"contents_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/contents/{+path}",
"compare_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/compare/{base}...{head}",
"merges_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/merges",
"archive_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/{archive_format}{/ref}",
"downloads_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/downloads",
"issues_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/issues{/number}",
"pulls_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/pulls{/number}",
"milestones_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/milestones{/number}",
"notifications_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/notifications{?since,all,participating}",
"labels_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/labels{/name}",
"releases_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/releases{/id}",
"deployments_url": "https://api.github.com/repos/Happynood/llm-inference-benchmark/deployments",
"created_at": "2026-06-13T16:38:53Z",
"updated_at": "2026-06-22T08:22:17Z",
"pushed_at": "2026-06-22T08:22:13Z",
"git_url": "git://github.com/Happynood/llm-inference-benchmark.git",
"ssh_url": "git@github.com:Happynood/llm-inference-benchmark.git",
"clone_url": "https://github.com/Happynood/llm-inference-benchmark.git",
"svn_url": "https://github.com/Happynood/llm-inference-benchmark",
"homepage": "",
"size": 1162,
"stargazers_count": 0,
"watchers_count": 0,
"language": "Python",
"has_issues": true,
"has_projects": true,
"has_downloads": true,
"has_wiki": true,
"has_pages": false,
"has_discussions": false,
"forks_count": 0,
"mirror_url": null,
"archived": false,
"disabled": false,
"open_issues_count": 2,
"license": {
"key": "mit",
"name": "MIT License",
"spdx_id": "MIT",
"url": "https://api.github.com/licenses/mit",
"node_id": "MDc6TGljZW5zZTEz"
},
"allow_forking": true,
"is_template": false,
"web_commit_signoff_required": false,
"has_pull_requests": true,
"pull_request_creation_policy": "all",
"topics": [
"benchmark",
"cuda",
"gguf",
"inference",
"llama-cpp",
"llama-cpp-python",
"llm",
"llm-inference",
"local-ai-llm",
"machine-learning",
"nvidia",
"perfomance",
"python",
"quantization",
"reproducibility"
],
"visibility": "public",
"forks": 0,
"open_issues": 2,
"watchers": 0,
"default_branch": "main",
"temp_clone_token": null,
"network_count": 0,
"subscribers_count": 0
}
}
]
}