A high-throughput and memory-efficient inference and serving engine for LLMs
active 2024-04-23 → 2025-03-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 331 days from 2024-04-23 to 2025-03-19. Pushes: 14 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 19 total, peak 3 in a day. Comments: 36 total, peak 9 in a day. Stars: 14 total, peak 1 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 |
|---|---|---|---|---|
| HwwwwwwwH | 20 | 13 | 0 | 6 |
| github-actions[bot] | 11 | 0 | 0 | 11 |
| renjingneng | 11 | 0 | 0 | 6 |
| yangJirui | 3 | 0 | 0 | 1 |
| blfletcher | 2 | 0 | 0 | 1 |
| NaLucia | 2 | 0 | 0 | 1 |
| qq745639151 | 2 | 0 | 0 | 1 |
| DiaQusNet | 2 | 0 | 0 | 1 |
| zjh908491372 | 1 | 0 | 0 | 0 |
| bingo-todd | 1 | 0 | 0 | 1 |
| ZamboLin | 1 | 0 | 0 | 1 |
| iceflame89 | 1 | 1 | 0 | 0 |
| xiechunhong | 1 | 0 | 0 | 1 |
| xiaohuihui52309 | 1 | 0 | 0 | 0 |
| ransheng11 | 1 | 0 | 0 | 1 |
| darrenzhang1007 | 1 | 0 | 0 | 1 |
| 128Ghe980 | 1 | 0 | 0 | 1 |
| pandaGst | 1 | 0 | 0 | 0 |
| Wyyyb | 1 | 0 | 0 | 1 |
| bravelll | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#11github-actions[bot]2025-03-13 02:40[Usage]: minicpm分支推理多图和视频的时候，跑完一帧会报这个warring就不继续推理了，也没有最终的结果输出。
- Issue comment#14github-actions[bot]2025-03-03 02:38[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue#15HwwwwwwwH2025-01-21 03:44[Bug]: use_beam_search not a supported parameter
- Issue comment#15blfletcher2025-01-19 17:19[Bug]: use_beam_search not a supported parameter
- Issue comment#15HwwwwwwwH2025-01-19 05:19[Bug]: use_beam_search not a supported parameter
- Issue#15blfletcher2025-01-19 05:07[Bug]: use_beam_search not a supported parameter
- Issue comment#2github-actions[bot]2025-01-14 02:28[Installation]: NameError: name 'vllm_ops' is not defined
- Issue comment#1github-actions[bot]2025-01-14 02:28[Bug]: ```text The output of `python minicpmv_example.py` ``` File "/data/envs/jh_llava/lib/python3.10/site-packages/vllm/model_executor/model_loader/utils.py", line 35, in get_model_architecture ValueError: Model architectures ['MiniCPMV'] are not supported for now. Supported architectures: 这个问题是环境版本的问题吗？ 如果是的话能提供一下正确的版本吗
- Issue comment#3github-actions[bot]2025-01-14 02:28[Usage]: 请问是否支持batch 推理？
- Issue comment#4github-actions[bot]2025-01-14 02:28[Usage]: 推理报错
- Issue comment#5github-actions[bot]2025-01-14 02:28多张卡推理Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:3!
- Issue comment#7github-actions[bot]2025-01-14 02:28[Doc]: minicpmv2 inference
- Issue comment#12github-actions[bot]2025-01-14 02:28[Bug]: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now. Supported architectures:
- Issue comment#9github-actions[bot]2025-01-14 02:28[Usage]: openbmb-MiniCPM-Llama3-V-2_5 在vllm上无法多gpu使用
- Issue comment#13github-actions[bot]2025-01-14 02:28[Installation]: Building wheel for vllm (pyproject.toml) did not run successfully
- Issue comment#11ransheng112024-12-12 11:22[Usage]: minicpm分支推理多图和视频的时候，跑完一帧会报这个warring就不继续推理了，也没有最终的结果输出。
- Issue comment#14guduzhixing2024-12-02 11:33[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue comment#14ZamboLin2024-12-02 01:43[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue comment#14bingo-todd2024-10-21 11:34[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue comment#14qq7456391512024-09-14 07:48[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue#14qq7456391512024-09-14 07:48[Installation]: 安装报告找不到numpy，实际nump已经安装好了
- Issue comment#13DiaQusNet2024-09-12 11:26[Installation]: Building wheel for vllm (pyproject.toml) did not run successfully
- Issue#13DiaQusNet2024-09-12 11:24[Installation]: Building wheel for vllm (pyproject.toml) did not run successfully
- Issue#12LeoMax-Xiong2024-09-12 09:40[Bug]: Model architectures ['MiniCPM3ForCausalLM'] are not supported for now. Supported architectures:
- Issue comment#11NaLucia2024-09-05 02:22[Usage]: minicpm分支推理多图和视频的时候，跑完一帧会报这个warring就不继续推理了，也没有最终的结果输出。
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 14 stars here means stars gained during the window, not the repo's star count.