openbmb/minicpm/minicpm5-deploy-arclight
Claude Code and agent skill by openbmb/minicpm
- community
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install openbmb/minicpm/minicpm5-deploy-arclightSKILL.md
The same SKILL.md was published earlier as openbmb/minicpm/minicpm5-deploy-arclight.
Deploy ArcLight from Source (CPU)
ArcLight is a lightweight C/C++ LLM inference framework for unified-memory systems. The recommended path is to build from source, then run a GGUF model with al-gen, al-chat, or al-ppl.
Required input
| Var | Example | Default | |
|---|---|---|---|
MODEL | /path/to/MiniCPM5-2B-Q4_0.gguf | required | |
PROMPT | "Hello!" | "Hello!" | |
THREADS | 4 | choose for the target CPU | |
NUMA_MODE | none or tp | none for first run | |
NODES | 1, 2, 4 | 1 with NUMA_MODE=none | |
MAX_GEN | 256 | 256 |
Steps
1. Build from source
Use ARCLIGHT_BACKEND=AUTO by default. Set it explicitly only when needed:
X86: force the x86 backendNEON: force the ARM NEON backendNONE: build without architecture-specific backend code
2. Prepare a GGUF model
ArcLight uses GGUF checkpoints from llama.cpp. The nnml backend only loads f32 / f16 / q4_0 / q8_0 / q6_K / q8_K tensor types — `Q4_K_M` is not supported.
Supported model families: MiniCPM5-2B, Qwen3, Llama2.
For first validation use the released Q8_0 (openbmb/MiniCPM5-2B-GGUF), or quantize an unreleased Q4_0 yourself from the F16:
3A. One-shot generation
3B. Interactive chat
To seed the first turn:
3C. Perplexity
Many-core CPU / NUMA
Start with single-node mode for correctness:
Use cross-NUMA tensor parallelism on many-core machines:
Rules:
--numa nonerequires--nodes 1.--numa tprequires--nodes NwhereN > 1.- In the current version,
NODESshould be a power of 2. - Choose
THREADSso it can be evenly divided acrossNODES. --numa ppis reserved for future pipeline parallelism and is not implemented.
Optional memory buffers
If allocation fails or the model is larger, pass manual buffer sizes:
Meaning:
--w_gb: weight buffer size--a_gb: activation buffer size--kv_gb: KV cache buffer size--work_gb: temporary workspace size
Increase --kv_gb for longer --max_length. Increase --w_gb for larger models.
Validate
Run:
The reply should contain 2 or a short explanation that evaluates to 2.
Common pitfalls
- Program aborts in single-node mode: use
--numa none --nodes 1. - Tensor parallel mode fails: use
--numa tp --nodes NwithN > 1; in this version,Nshould be a power of 2. - Pipeline parallelism fails:
--numa ppis not implemented yet. - Model loading fails: verify the checkpoint is GGUF and from a supported model family.
- Out of memory: increase
--w_gb,--a_gb,--kv_gb, or--work_gb; longer contexts usually need a larger KV cache. - Poor CPU throughput: check
--threads, NUMA layout, and thread-core bindings; use--print_binding 1 --print_perf 1for diagnostics.
When NOT to use
- Need CUDA server inference -> use a GPU-oriented runtime instead.
- Need Apple Silicon MLX inference -> use an MLX deployment path instead.
- Need a desktop GUI -> use a GUI runtime that supports GGUF models.
- Need pipeline parallelism -> wait for ArcLight
--numa ppsupport.
Reference
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/minicpm5-deploy-arclight/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-arclight)