DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
active 2025-03-08 → 2026-03-24 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 382 days from 2025-03-08 to 2026-03-24. Pushes: 11 total, peak 2 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 8 total, peak 3 in a day. Comments: 46 total, peak 12 in a day. Stars: 23 total, peak 2 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 |
|---|---|---|---|---|
| kzjeef | 28 | 5 | 5 | 10 |
| gemini-code-assist[bot] | 12 | 0 | 0 | 9 |
| x574chen | 9 | 0 | 2 | 5 |
| coder4nlp | 5 | 0 | 0 | 5 |
| laiwenzh | 4 | 2 | 2 | 0 |
| github-merge-queue[bot] | 4 | 4 | 0 | 0 |
| mitu626 | 1 | 0 | 0 | 1 |
| Arthesfan | 1 | 0 | 0 | 1 |
| Hongtao-Xu | 1 | 0 | 0 | 1 |
| TITONIChen | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#93kzjeef2025-08-06 15:59multimodal: length configure should be again .
- Issue#93kzjeef2025-08-06 15:59multimodal: length configure should be again .
- Pull request#94kzjeef2025-08-06 15:59
- Issue comment#94gemini-code-assist[bot]2025-08-06 11:45read max model len from hf config
- Issue comment#92x574chen2025-07-31 05:35TRT Support for Qwen2.5VL Error.
- Issue comment#92kzjeef2025-07-31 04:29TRT Support for Qwen2.5VL Error.
- Issue comment#92kzjeef2025-07-31 03:53TRT Support for Qwen2.5VL Error.
- Issue#92kzjeef2025-07-31 03:53TRT Support for Qwen2.5VL Error.
- Issue comment#92kzjeef2025-07-31 03:36TRT Support for Qwen2.5VL Error.
- Issue#92kzjeef2025-07-31 03:36TRT Support for Qwen2.5VL Error.
- Issue comment#92kzjeef2025-07-30 03:14TRT Support for Qwen2.5VL Error.
- Pull request#91x574chen2025-07-29 11:13
- Pull request#91x574chen2025-07-29 11:04
- Releasekzjeef2025-07-29 06:54v2.2.1
- Issue comment#89coder4nlp2025-07-28 12:40The inference time of qwen2.5-vl is very slow.
- Pull request#90kzjeef2025-07-28 12:07
- Issue comment#89kzjeef2025-07-28 11:15The inference time of qwen2.5-vl is very slow.
- Issue comment#89coder4nlp2025-07-28 06:16The inference time of qwen2.5-vl is very slow.
- Issue comment#89kzjeef2025-07-28 03:42The inference time of qwen2.5-vl is very slow.
- Issue comment#89coder4nlp2025-07-28 03:19The inference time of qwen2.5-vl is very slow.
- Issue comment#89kzjeef2025-07-24 14:00The inference time of qwen2.5-vl is very slow.
- Issue comment#89coder4nlp2025-07-24 12:49The inference time of qwen2.5-vl is very slow.
- Issue comment#89kzjeef2025-07-24 09:53The inference time of qwen2.5-vl is very slow.
- Issue comment#89coder4nlp2025-07-24 09:28The inference time of qwen2.5-vl is very slow.
- Issue comment#89coder4nlp2025-07-24 09:18The inference time of qwen2.5-vl is very slow.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 23 stars here means stars gained during the window, not the repo's star count.