MiniCPM is a family of compact language models, including MiniCPM5-1B, designed to run locally on devices with limited resources. Developers use it for on-device assistants, reasoning, code, tool use, deployment, and fine-tuning, while the repository also includes a desktop-pet example. The catalogue entries support deployment and fine-tuning workflows for the models.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenBMB/MiniCPM --skill minicpm5-deploy-vllm-ascendgit clone --depth 1 https://github.com/OpenBMB/MiniCPMWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-vllm-ascend)<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-vllm-ascend"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-vllm-ascend/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-vllm-ascend"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-vllm-ascend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.01941 |
| Opus 5 | $0.00044 | $0.00971 |
| Sonnet 5 | $0.00017 | $0.00388 |
| Haiku 4.5 | $0.00009 | $0.00194 |
Grade A, and why
minicpm5-deploy-vllm-ascend scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:${PORT:-8000}/v1/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy MiniCPM5-2B with vLLM-Ascend
Use this skill for the BF16 / FP16 openbmb/MiniCPM5-2B checkpoint on Huawei Ascend NPU. vllm-ascend is installed alongside a matching vLLM release and supplies the Ascend backend.
Required input
| Variable | Example | Default |
|---|---|---|
MODEL_PATH |
openbmb/MiniCPM5-2B |
required |
PORT |
8000 |
8000 |
ASCEND_RT_VISIBLE_DEVICES |
0 |
0 |
CTX_LEN |
32768 |
32768; the native maximum is 131072 |
MEM_FRAC |
0.85 |
0.85 |
TP_SIZE |
1 |
number of visible devices |
Accept either the Hugging Face id or a local directory containing the MiniCPM5-2B model files.
Prerequisites
Use a compatible Linux Ascend environment with CANN, PyTorch, and TorchNPU installed. Keep the vLLM and vLLM-Ascend versions matched. The basic serving recipe below follows the tested vllm==0.18.0 / vllm-ascend==0.18.0 pair.
Device visibility is controlled by ASCEND_RT_VISIBLE_DEVICES; CUDA_VISIBLE_DEVICES does not select Ascend devices.
Install
The prebuilt image is the simplest option for a compatible Ascend host. This is a minimal single-device example; adjust device nodes and driver mounts for the host hardware and image documentation.
docker run -it --net=host --shm-size=1g \
--device /dev/davinci0 --device /dev/davinci_manager \
--device /dev/devmm_svm --device /dev/hisi_hdc \
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
quay.io/ascend/vllm-ascend:v0.18.0
For an existing CANN environment:
pip install vllm==0.18.0 vllm-ascend==0.18.0 \
--extra-index-url https://download.pytorch.org/whl/cpu
For built-in MiniCPM5 tool-call parsing, use the matching vllm==0.23.0 / vllm-ascend==0.23.0 stack described in Tool calling. The parser responses in the cookbook were produced with the upstream parser file on an older vLLM and a compatibility shim because the 0.23.0 stack was not available on the test hardware.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 168 lines · 87 tokens per session scan A 511fbd5c7b46
minicpm5-deploy-vllm-ascend is a skill published in the GitHub repository OpenBMB/MiniCPM (10,780 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 1,941 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
amc-run-video-calibration
Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.