Metadata-Version: 2.4
Name: ckg-nvidia-nemotron
Version: 0.1.1
Summary: Compressed Knowledge Graph for NVIDIA Nemotron 3 Ultra 550B A55B — 71 nodes, 120+ edges. Architecture, training pipeline, reasoning modes, deployment, benchmarks, and agentic integrations.
Project-URL: Homepage, https://graphifymd.com/pro/
Project-URL: Repository, https://github.com/Yarmoluk/ckg-nvidia-nemotron
Project-URL: Documentation, https://github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf
Author-email: Daniel Yarmoluk <daniel.yarmoluk@gmail.com>
License: MIT
Keywords: ai-agents,ckg,graphifymd,knowledge-graph,llm,mcp,model-context-protocol,nemotron,nvidia,reasoning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Requires-Dist: fastmcp>=0.4.0
Requires-Dist: mcp[cli]>=1.3.0
Requires-Dist: starlette>=0.41.0
Requires-Dist: uvicorn>=0.30.0
Description-Content-Type: text/markdown

# ckg-nvidia-nemotron

**Compressed Knowledge Graph · NVIDIA Nemotron 3 Ultra 550B A55B**

71 nodes · 120+ edges · architecture, training pipeline, reasoning modes, deployment, benchmarks, agentic integrations.

Traversable via MCP — agents query declared relationships instead of inferring them.

```bash
pip install ckg-nvidia-nemotron
```

## What's in the graph

| Category | Concepts |
|---|---|
| Architecture | Hybrid Mamba-Transformer MoE, LatentMoE, MTP layers, 1M context |
| Training | 20T tokens (NVFP4), 7 stages: Pretrain → SFT → RLVR → MOPD → MTP Boosting |
| RLVR | DAPO (NeMo RL), GRPO (NeMo Gym), 6 reward domains |
| MOPD | 10+ teacher models, 2 iterative distillation rounds |
| Reasoning | Off / Regular / Medium + Reasoning Budget Control |
| Deployment | vLLM, SGLang, TensorRT-LLM, NIM Microservices |
| Hardware | DGX Cluster (4-node), GB300 DGX Station (selective expert offloading) |
| Parallelism | TP=2, PP=6/12, EP=32 |
| Fine-tuning | LoRA via NeMo AutoModel, Megatron-Bridge, Unsloth |
| Agentic | Hermes Agent, OpenClaw, tool use, multi-step planning, deep research |
| Benchmarks | Intelligence Index 47.7, IFBench 81.4%, Ruler 95%, PinchBench 91%, Terminal-Bench 54% |
| Pricing | $0.50/$2.20 per 1M tokens (NIM API) |

## MCP tools

- **`search_concepts(query)`** — keyword search across all 70 nodes
- **`query_ckg(concept, depth)`** — subgraph traversal (1–3 hops)
- **`get_prerequisites(concept)`** — full upstream dependency chain
- **`list_domains()`** — package metadata
- **`get_benchmark_summary()`** — scores, competitive positioning, pricing
- **`get_deployment_guide(target)`** — nim / vllm / sglang / tensorrt / fine-tuning

## Usage

### Claude Desktop / Cursor / Claude Code

```json
{
  "mcpServers": {
    "ckg-nvidia-nemotron": {
      "command": "uvx",
      "args": ["ckg-nvidia-nemotron"]
    }
  }
}
```

### Python

```python
from ckg_nvidia_nemotron.server import search_concepts, query_ckg, get_prerequisites

# Find the LatentMoE routing architecture
print(search_concepts("LatentMoE"))

# Traverse training pipeline
print(query_ckg("MOPD", depth=2))

# What must be in place before reasoning modes work?
print(get_prerequisites("Reasoning Mode Medium"))
```

### HTTP server

```bash
ckg-nvidia-nemotron --port 8000
# MCP endpoint: POST http://localhost:8000/mcp
```

## Benchmark

Grounded in the Compact Knowledge Graph benchmark (v0.6.2).

## EVAL
```
benchmark: ckg-benchmark v0.6.2
dataset: huggingface.co/datasets/danyarm/ckg-benchmark
benchmarked: false
rag_baseline_f1: 0.123
graphrag_baseline_f1: 0.120
mean_tokens: 269
paper: github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf
```

## META
```
version: 0.1.1
domain: nvidia-nemotron
nodes: 71
edges: 120+
model_covered: Nemotron 3 Ultra 550B A55B
nvidia_release_date: 2026-06-04
license_of_model: OpenMDW-1.1
package_license: MIT
publisher: Graphify.md
publisher_url: https://graphifymd.com/pro/
```

---

Built by [Graphify.md](https://graphifymd.com) · [Benchmark paper](https://github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf) · patent pending
