🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.
active 2024-01-31 → 2025-08-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 557 days from 2024-01-31 to 2025-08-09. Pushes: 115 total, peak 16 in a day. Pull requests: 42 total, peak 5 in a day. Issues: 47 total, peak 19 in a day. Comments: 122 total, peak 22 in a day. Stars: 127 total, peak 24 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 |
|---|---|---|---|---|
| Anindyadeep | 254 | 92 | 28 | 75 |
| nsosio | 132 | 17 | 13 | 43 |
| github-actions[bot] | 6 | 6 | 0 | 0 |
| lopuhin | 4 | 0 | 0 | 3 |
| Interpause | 2 | 0 | 0 | 1 |
| rohitgr7 | 1 | 0 | 0 | 0 |
| IlyasMoutawwakil | 1 | 0 | 0 | 0 |
| ogencoglu | 1 | 0 | 0 | 0 |
| swarnimarun | 1 | 0 | 1 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#191IlyasMoutawwakil2025-05-09 16:11Onnxruntime is not using kv cache nor io binding 😅
- Issue comment#190Anindyadeep2024-07-25 18:46Llamacpp cpu support
- Pull request#190Anindyadeep2024-07-25 18:39
- Pull request#189Anindyadeep2024-07-17 08:02
- Issue comment#189Anindyadeep2024-07-17 08:02update: candle to latest & pin version
- Pull request#189swarnimarun2024-06-07 09:10
- Issue comment#187Anindyadeep2024-06-03 14:53Incorrect results reported for TensorRT-LLM
- Issue comment#187lopuhin2024-06-03 13:54Incorrect results reported for TensorRT-LLM
- Issue comment#187lopuhin2024-06-03 10:51Incorrect results reported for TensorRT-LLM
- Issue comment#187lopuhin2024-06-03 10:41Incorrect results reported for TensorRT-LLM
- Issue comment#187Anindyadeep2024-06-02 13:45Incorrect results reported for TensorRT-LLM
- Issue#188Anindyadeep2024-06-01 02:37Max Engine by Mojo
- Issue#187lopuhin2024-05-17 11:26Incorrect results reported for TensorRT-LLM
- Issue comment#185Anindyadeep2024-05-15 06:22Use exllamav2's smart 4-bit KV cache for memory benchmark
- Issue#185Interpause2024-05-14 07:39Use exllamav2's smart 4-bit KV cache for memory benchmark
- Issue comment#43Interpause2024-05-14 07:35Ollama
- Issue comment#102Anindyadeep2024-04-29 18:14Benchmark along with a modular inference endpoint provider.
- Issue#102Anindyadeep2024-04-29 18:14Benchmark along with a modular inference endpoint provider.
- Issue comment#162Anindyadeep2024-04-29 18:13For quality checks reference should be taken from actual PyTorch version of model
- Issue#162Anindyadeep2024-04-29 18:13For quality checks reference should be taken from actual PyTorch version of model
- Issue comment#106Anindyadeep2024-04-29 18:12We should also include the memory consumption for the devices.
- Issue#106Anindyadeep2024-04-29 18:12We should also include the memory consumption for the devices.
- Issue comment#157Anindyadeep2024-04-29 18:12Improvements on logging and storing results
- Issue#157Anindyadeep2024-04-29 18:12Improvements on logging and storing results
- Issue#91Anindyadeep2024-04-29 18:11Code modularity, refactoring and re-usability.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 127 stars here means stars gained during the window, not the repo's star count.