MLCommons Inference Endpoints repository
active 2026-04-03 → 2026-08-18 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 138 days from 2026-04-03 to 2026-08-18. Pushes: 220 total, peak 15 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 39 total, peak 28 in a day. Comments: 149 total, peak 13 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| arekay-nv | 127 | 80 | 1 | 32 |
| viraatc | 104 | 84 | 4 | 10 |
| nvzhihanj | 73 | 15 | 1 | 14 |
| nv-alicheng | 50 | 13 | 0 | 21 |
| Copilot | 31 | 1 | 0 | 20 |
| wu6u3tw | 27 | 2 | 1 | 13 |
| tianmu-li | 20 | 0 | 0 | 9 |
| gemini-code-assist[bot] | 16 | 0 | 0 | 11 |
| github-code-quality[bot] | 15 | 0 | 0 | 8 |
| anandhu-eng | 12 | 12 | 0 | 0 |
| merlinf31 | 8 | 6 | 0 | 0 |
| attafosu | 5 | 3 | 1 | 1 |
| wangshangsam | 5 | 0 | 0 | 2 |
| Victor49152 | 5 | 1 | 1 | 1 |
| hvagadia | 4 | 2 | 0 | 2 |
| github-actions[bot] | 4 | 0 | 0 | 4 |
| leopck | 1 | 0 | 0 | 0 |
| AzeezIsh | 1 | 0 | 0 | 1 |
| arav-agarwal2 | 1 | 1 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#433arekay-nv2026-08-12 16:37fix(lcb-service): use the fork start method explicitly
- Issue comment#334viraatc2026-06-30 23:21feat: add -vvv trace mode dashboard for client overhead
- Issue#384viraatc2026-06-30 21:08Refactor commands/benchmark/execute.py — split the benchmark God-module
- Issue comment#350nv-alicheng2026-06-27 00:39perf(metrics): batch tokenization with defer-to-flush drain
- Pull request#375attafosu2026-06-25 01:15
- Issue comment#346AzeezIsh2026-06-09 05:09feat(bfcl): add BFCL v4 edge-agentic accuracy integration
- Issue comment#344nvzhihanj2026-06-07 05:27feat: Enable per dataset max-osl
- Pull request#344arekay-nv2026-06-06 21:36
- Pull request#343viraatc2026-06-06 00:45
- Issue comment#332wu6u3tw2026-06-04 22:57feat(compliance): add MLPerf TEST04 caching audit mode
- Issue comment#322attafosu2026-05-20 23:42[GPT-OSS] Accuracy and performance config differences - Reasoning effort
- Issue comment#314arekay-nv2026-05-19 23:40Agentic Inference updates
- Issue#313tianmu-li2026-05-15 22:14[Feature]: Inline accuracy check of performance runs
- Issue#313tianmu-li2026-05-15 22:14[Feature]: Inline accuracy check of performance runs
- Issue#312tianmu-li2026-05-15 22:13[Feature]: cache salting for multi-turn
- Issue comment#306nv-alicheng2026-05-11 20:53Change MetricsAggregatorService to publisher to support live metrics without shmem
- Issue comment#308github-actions[bot]2026-05-09 11:38feat: add OpenAI /v1/completions adapter for vLLM gpt-oss-120b accuracy
- Issue comment#293arekay-nv2026-05-06 05:29feat(wan22): add WAN 2.2 text-to-video adapter and dataset for MLPerf inference
- Issue comment#300github-actions[bot]2026-04-28 23:11refactor: generalize ZMQ pub/sub over message type via MessageCodec
- Issue comment#296github-actions[bot]2026-04-28 01:42feat: Consolidate llama examples
- Pull request#293wu6u3tw2026-04-22 22:25
- Pull request#291viraatc2026-04-22 19:41
- Issue#289wu6u3tw2026-04-21 19:52[Discussion] Video Return Format and Transmission Overhead in Inference Performance
- Issue#289wu6u3tw2026-04-21 19:52[Discussion] Video Return Format and Transmission Overhead in Inference Performance
- Issue#289wu6u3tw2026-04-21 19:52[Discussion] Video Return Format and Transmission Overhead in Inference Performance
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.