openbmb/minicpm/minicpm5-deploy-sglang
Claude Code and agent skill by openbmb/minicpm
- community
Checking that the SKILL.md file is still in the repository.
Serve MiniCPM5-1B or MiniCPM5-2B via SGLang as an OpenAI-compatible HTTP server with RadixAttention prefix cache and built-in MiniCPM5 tool-call parsing. Use when the user asks for "SGLang", "RadixAttention", "prefix cache", batch evaluation, tool calling, or wants a high-concurrency NVIDIA-GPU server alternative to vLLM.
Install
npx vskill@latest install openbmb/minicpm/minicpm5-deploy-sglangSKILL.md
The same SKILL.md was published earlier as openbmb/minicpm/minicpm5-deploy-sglang.
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)
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:
2. Recommended runtime env vars
3. Launch
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:
4. Validate
Expected: choices[0].message.content contains "2".
Tool calling
SGLang includes a native MiniCPM5 XML tool-call parser. Keep TOOL_PARSER=minicpm5 (or auto) when launching, then send an OpenAI-style tools request:
Offline / batched (Engine API)
Common pitfalls
- `GLIBCXX_3.4.31 not found` (only if you hit it — not universal): conda Python ships an older
libstdc++than the SGLang wheel was built against. Force-load the system one:LD_PRELOAD=/lib/x86_64-linux-gnu/libstdc++.so.6 python -m sglang.launch_server ...
When NOT to use
- Production serving without batch-eval needs →
minicpm5-deploy-vllmis simpler - One-shot Python →
minicpm5-deploy-transformers - No NVIDIA GPU →
minicpm5-deploy-llama-cpp/minicpm5-deploy-mlx
Reference
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/minicpm5-deploy-sglang/SKILL.md
Popularity
- Repository stars
- 9,518
- Repository forks
- 625
- 7-day trend score
- 46
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/openbmb/minicpm/minicpm5-deploy-sglang)