minicpm5-deploy-sglang

minicpm5-deploy-sglang is a skill for Claude Code, Codex from OpenBMB/MiniCPM. It costs 96 tokens per session (1,554 once invoked), scanned A, original, Apache-2.0.

Instructions for serving the MiniCPM5-1B language model through SGLang, a system for running language models behind an HTTP service. The service follows the OpenAI API format and includes support for cached shared prompts and tool calls.

In plain words
What is it for?
Use it to deploy MiniCPM5-1B on an NVIDIA GPU, expose an OpenAI-compatible server, evaluate batches of prompts, and enable tool calling.
Why use it?
It provides a documented way to run this model for concurrent requests, batch evaluations, and applications that let the model call tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to deploy MiniCPM5-1B on an NVIDIA GPU, expose an OpenAI-compatible server, evaluate batches of prompts, and enable tool calling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openbmb/minicpm/minicpm5-deploy-sglang
About the project

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.

OpenBMB/MiniCPM · 10,673 stars · on GitHub

Install

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.

Any agent
npx skills add OpenBMB/MiniCPM --skill minicpm5-deploy-sglang
Clone the repo
git clone --depth 1 https://github.com/OpenBMB/MiniCPM

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for minicpm5-deploy-sglang

README.md
[![agentmods](https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-sglang/github.svg)](https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-sglang)
Your own site
<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-sglang"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-sglang/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.

agentmods 80×15 button for minicpm5-deploy-sglang

Your own site · 80×15
<a href="https://agentmods.dev/skills/openbmb/minicpm/minicpm5-deploy-sglang"><img src="https://agentmods.dev/badge/skills/openbmb/minicpm/minicpm5-deploy-sglang.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high YARA Match · line 120
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • medium Data Exfiltration · line 63
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.01554
Opus 5 $0.00048 $0.00777
Sonnet 5 $0.00019 $0.00311
Haiku 4.5 $0.00010 $0.00155

Measured 2d ago against content hash 19950c893641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

minicpm5-deploy-sglang 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}/v1/chat/completions \
skills/minicpm5-deploy-sglang/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy MiniCPM5-1B and MiniCPM5-2B with SGLang

OpenAI-compatible server with RadixAttention prefix cache. Best fit for tool calling, batched eval pipelines, and high-concurrency serving.

Required input

Var Example Default
MODEL_PATH openbmb/MiniCPM5-2B or openbmb/MiniCPM5-1B required;
PORT 30000 30000
GPU_ID 0 0
CTX_LEN 131072 (128 K) 131072
MEM_FRAC 0.85 0.85
TOOL_PARSER minicpm5 minicpm5; use auto if you want template detection

Steps

1. Install (once)

pip install "sglang[srt]>=0.5.16"          # latest, requires CUDA 13.x driver
# pip install "sglang==0.5.6.post3"        # fallback for CUDA 12.x driver hosts

For tool calling, install from main — the minicpm5 parser (PR #25600, merged 2026-05-22) is not in any pip release yet (v0.5.12.post1 was branched earlier). Plain chat works on the pip release; only --tool-call-parser minicpm5 needs main:

pip install "git+https://github.com/sgl-project/sglang.git@main#subdirectory=python"

2. Recommended runtime env vars

export VLLM_WORKER_MULTIPROC_METHOD=spawn
export SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
export SGLANG_DISABLE_CUDNN_CHECK=1

3. Launch

CUDA_VISIBLE_DEVICES=${GPU_ID} python -m sglang.launch_server \
    --model-path "${MODEL_PATH}" \
    --served-model-name MiniCPM5-2B \
    --dtype bfloat16 \
    --context-length ${CTX_LEN} \
    --mem-fraction-static ${MEM_FRAC} \
    --tool-call-parser ${TOOL_PARSER} \
    --host 0.0.0.0 \
    --port ${PORT}

Wait for The server is fired up and ready to roll! .

Speculative decoding (DSpark): we also release MiniCPM5-2B-DSpark, a DSpark draft model trained for MiniCPM5-2B. Enable it in SGLang to accelerate decoding while keeping the target model's outputs unchanged:

Read the full file on GitHub · 148 lines

Changes

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.

  1. 2d ago Changed · +17 lines · +8 tokens per session 19950c893641
  2. 10d ago First seen · 131 lines · 88 tokens per session scan A de78e5d65c5e

Subscribe to this mod's changes

minicpm5-deploy-sglang is a skill published in the GitHub repository OpenBMB/MiniCPM (10,673 stars, last pushed 2d ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,554 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens