sarman/dgx-spark-playbooks
1
0
Fork 0
mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-22 18:13:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/jasonkneen/dgx-spark-playbooks

Browse Source
This commit is contained in:
Jason Kneen 2026-04-19 11:40:41 +01:00
commit 34cd09b53e
41 changed files with 41 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
skills/dgx-spark-comfy-ui/SKILL.md
View File

@ -16,5 +16,5 @@ Workflows are saved as JSON files, so you can version them for future work, coll
**Outcome**: You'll install and configure ComfyUI on your NVIDIA DGX Spark device so you can use the unified memory to work with large models. **Outcome**: You'll install and configure ComfyUI on your NVIDIA DGX Spark device so you can use the unified memory to work with large models.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/comfy-ui/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/comfy-ui/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-connect-three-sparks/SKILL.md
View File

@ -16,5 +16,5 @@ DGX Spark nodes by establishing network connectivity and configuring SSH authent
interfaces for cluster communication, and establish passwordless SSH between nodes to create interfaces for cluster communication, and establish passwordless SSH between nodes to create
a functional distributed computing environment. a functional distributed computing environment.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/connect-three-sparks/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/connect-three-sparks/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-connect-to-your-spark/SKILL.md
View File

@ -22,7 +22,7 @@ integrated app launching, while manual SSH gives you direct command-line control
forwarding capabilities. Both approaches enable you to run terminal commands, access web forwarding capabilities. Both approaches enable you to run terminal commands, access web
applications, and manage your DGX Spark remotely from your laptop. applications, and manage your DGX Spark remotely from your laptop.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/connect-to-your-spark/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/connect-to-your-spark/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->
## When to use this skill ## When to use this skill

2
skills/dgx-spark-connect-two-sparks/SKILL.md
View File

@ -16,5 +16,5 @@ by establishing network connectivity and configuring SSH authentication.
interfaces for cluster communication, and establish passwordless SSH between nodes to create interfaces for cluster communication, and establish passwordless SSH between nodes to create
a functional distributed computing environment. a functional distributed computing environment.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/connect-two-sparks/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/connect-two-sparks/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-cuda-x-data-science/SKILL.md
View File

@ -17,5 +17,5 @@ CUDA-X Data Science (formally RAPIDS) is an open-source library collection that
**Outcome**: You will accelerate popular machine learning algorithms and data analytics operations GPU. You will understand how to accelerate popular Python tools, and the value of running data science workflows on your DGX Spark. **Outcome**: You will accelerate popular machine learning algorithms and data analytics operations GPU. You will understand how to accelerate popular Python tools, and the value of running data science workflows on your DGX Spark.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/cuda-x-data-science/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/cuda-x-data-science/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-dgx-dashboard/SKILL.md
View File

@ -12,5 +12,5 @@ The DGX Dashboard is a web application that runs locally on DGX Spark devices, p
**Outcome**: You will learn how to access and use the DGX Dashboard on your DGX Spark device. By the end of this walkthrough, you will be able to launch JupyterLab instances with pre-configured Python environments, monitor GPU performance, manage system updates, and run a sample AI workload using Stable Diffusion. You'll understand multiple access methods including desktop shortcuts, NVIDIA Sync, and manual SSH tunneling. **Outcome**: You will learn how to access and use the DGX Dashboard on your DGX Spark device. By the end of this walkthrough, you will be able to launch JupyterLab instances with pre-configured Python environments, monitor GPU performance, manage system updates, and run a sample AI workload using Stable Diffusion. You'll understand multiple access methods including desktop shortcuts, NVIDIA Sync, and manual SSH tunneling.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/dgx-dashboard/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/dgx-dashboard/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-flux-finetuning/SKILL.md
View File

@ -24,5 +24,5 @@ The setup includes:
Duration: * 30-45 minutes for initial setup model download time Duration: * 30-45 minutes for initial setup model download time
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/flux-finetuning/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/flux-finetuning/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-isaac/SKILL.md
View File

@ -14,5 +14,5 @@ Isaac Sim uses GPU-accelerated physics simulation to enable fast, realistic robo
**Outcome**: You'll build Isaac Sim from source on your NVIDIA DGX Spark device and set up Isaac Lab for reinforcement learning experiments. This includes compiling the Isaac Sim engine, configuring the development environment, and running a sample RL training task to verify the installation. **Outcome**: You'll build Isaac Sim from source on your NVIDIA DGX Spark device and set up Isaac Lab for reinforcement learning experiments. This includes compiling the Isaac Sim engine, configuring the development environment, and running a sample RL training task to verify the installation.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/isaac/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/isaac/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-jax/SKILL.md
View File

@ -21,5 +21,5 @@ JAX lets you write **NumPy-style Python code** and run it fast on GPUs without w
high-performance machine learning prototyping using familiar NumPy-like abstractions, complete with high-performance machine learning prototyping using familiar NumPy-like abstractions, complete with
GPU acceleration and performance optimization capabilities. GPU acceleration and performance optimization capabilities.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/jax/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/jax/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-live-vlm-webui/SKILL.md
View File

@ -20,5 +20,5 @@ The interface provides WebRTC-based video streaming, integrated GPU monitoring,
- Customize prompts for various use cases (object detection, scene description, OCR, safety monitoring) - Customize prompts for various use cases (object detection, scene description, OCR, safety monitoring)
- Access the interface from any device on your network with a web browser - Access the interface from any device on your network with a web browser
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/live-vlm-webui/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/live-vlm-webui/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-llama-cpp/SKILL.md
View File

@ -18,5 +18,5 @@ This playbook walks through that stack end to end. As the model example, it uses
- An OpenAI-compatible `/v1/chat/completions` endpoint for tools and apps - An OpenAI-compatible `/v1/chat/completions` endpoint for tools and apps
- A concrete validation that **Gemma 4 31B IT** runs on this stack on DGX Spark - A concrete validation that **Gemma 4 31B IT** runs on this stack on DGX Spark
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/llama-cpp/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/llama-cpp/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-llama-factory/SKILL.md
View File

@ -18,5 +18,5 @@ large language models using LLaMA Factory CLI on your NVIDIA Spark device.
language models using LoRA, QLoRA, and full fine-tuning methods. This enables efficient language models using LoRA, QLoRA, and full fine-tuning methods. This enables efficient
model adaptation for specialized domains while leveraging hardware-specific optimizations. model adaptation for specialized domains while leveraging hardware-specific optimizations.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/llama-factory/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/llama-factory/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-lm-studio/SKILL.md
View File

@ -21,5 +21,5 @@ This playbook shows you how to deploy LM Studio on an NVIDIA DGX Spark device to
- Interact with models from your laptop using the LM Studio SDK - Interact with models from your laptop using the LM Studio SDK
- Optionally use **LM Link** to connect Spark and laptop over an encrypted link so remote models appear as local (no same-network or bind setup required) - Optionally use **LM Link** to connect Spark and laptop over an encrypted link so remote models appear as local (no same-network or bind setup required)
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/lm-studio/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/lm-studio/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-multi-agent-chatbot/SKILL.md
View File

@ -23,5 +23,5 @@ The setup includes:
- Multi-agent system orchestration using a supervisor agent powered by gpt-oss-120B - Multi-agent system orchestration using a supervisor agent powered by gpt-oss-120B
- MCP (Model Context Protocol) servers as tools for the supervisor agent - MCP (Model Context Protocol) servers as tools for the supervisor agent
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/multi-agent-chatbot/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/multi-agent-chatbot/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-multi-modal-inference/SKILL.md
View File

@ -19,5 +19,5 @@ FP8, FP4).
Duration: 45-90 minutes depending on model downloads and optimization steps Duration: 45-90 minutes depending on model downloads and optimization steps
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/multi-modal-inference/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/multi-modal-inference/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-multi-sparks-through-switch/SKILL.md
View File

@ -10,5 +10,5 @@ description: Set up a cluster of DGX Spark devices that are connected through Sw
Configure four DGX Spark systems for high-speed inter-node communication using 200Gbps QSFP connections through a QSFP switch. This setup enables distributed workloads across multiple DGX Spark nodes by establishing network connectivity and configuring SSH authentication. Configure four DGX Spark systems for high-speed inter-node communication using 200Gbps QSFP connections through a QSFP switch. This setup enables distributed workloads across multiple DGX Spark nodes by establishing network connectivity and configuring SSH authentication.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/multi-sparks-through-switch/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/multi-sparks-through-switch/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nccl/SKILL.md
View File

@ -19,5 +19,5 @@ and proper GPU topology detection.
Duration: 30 minutes for setup and validation · Risk: Medium - involves network configuration changes Duration: 30 minutes for setup and validation · Risk: Medium - involves network configuration changes
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nccl/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nccl/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nemo-fine-tune/SKILL.md
View File

@ -12,5 +12,5 @@ This playbook guides you through setting up and using NVIDIA NeMo AutoModel for
**Outcome**: You'll establish a complete fine-tuning environment for large language models (1-70B parameters) and vision-language models using NeMo AutoModel on your NVIDIA Spark device. By the end, you'll have a working installation that supports parameter-efficient fine-tuning (PEFT), supervised fine-tuning (SFT), and distributed training capabilities with FP8 precision optimizations, all while maintaining compatibility with the Hugging Face ecosystem. **Outcome**: You'll establish a complete fine-tuning environment for large language models (1-70B parameters) and vision-language models using NeMo AutoModel on your NVIDIA Spark device. By the end, you'll have a working installation that supports parameter-efficient fine-tuning (PEFT), supervised fine-tuning (SFT), and distributed training capabilities with FP8 precision optimizations, all while maintaining compatibility with the Hugging Face ecosystem.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nemo-fine-tune/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nemo-fine-tune/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nemoclaw/SKILL.md
View File

@ -26,5 +26,5 @@ By the end of this playbook you will have a working AI agent inside an OpenShell
### Notice and disclaimers ### Notice and disclaimers
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nemoclaw/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nemoclaw/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nemotron/SKILL.md
View File

@ -18,5 +18,5 @@ This playbook demonstrates how to run Nemotron-3-Nano using llama.cpp, which com
- OpenAI-compatible API endpoint for easy integration with existing tools - OpenAI-compatible API endpoint for easy integration with existing tools
- Built-in reasoning and tool calling capabilities - Built-in reasoning and tool calling capabilities
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nemotron/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nemotron/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nim-llm/SKILL.md
View File

@ -25,5 +25,5 @@ You'll launch a NIM container on your DGX Spark device to expose a GPU-accelerat
- Basic familiarity with REST APIs and curl commands - Basic familiarity with REST APIs and curl commands
- Understanding of NVIDIA GPU environments and CUDA - Understanding of NVIDIA GPU environments and CUDA
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nim-llm/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nim-llm/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-nvfp4-quantization/SKILL.md
View File

@ -23,5 +23,5 @@ inside a TensorRT-LLM container, producing an NVFP4 quantized model for deployme
The examples use NVIDIA FP4 quantized models which help reduce model size by approximately 2x by reducing the precision of model layers. The examples use NVIDIA FP4 quantized models which help reduce model size by approximately 2x by reducing the precision of model layers.
This quantization approach aims to preserve accuracy while providing significant throughput improvements. However, it's important to note that quantization can potentially impact model accuracy - we recommend running evaluations to verify if the quantized model maintains acceptable performance for your use case. This quantization approach aims to preserve accuracy while providing significant throughput improvements. However, it's important to note that quantization can potentially impact model accuracy - we recommend running evaluations to verify if the quantized model maintains acceptable performance for your use case.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/nvfp4-quantization/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/nvfp4-quantization/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-ollama/SKILL.md
View File

@ -21,7 +21,7 @@ the powerful GPU capabilities of your Spark device without complex network confi
Duration: 10-15 minutes for initial setup, 2-3 minutes for model download (varies by model size) · Risk: Low - No system-level changes, easily reversible by stopping the custom app Duration: 10-15 minutes for initial setup, 2-3 minutes for model download (varies by model size) · Risk: Low - No system-level changes, easily reversible by stopping the custom app
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/ollama/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/ollama/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->
## When to use this skill ## When to use this skill

2
skills/dgx-spark-open-webui/SKILL.md
View File

@ -15,7 +15,7 @@ This playbook shows you how to deploy Open WebUI with an integrated Ollama serve
Duration: 15-20 minutes for initial setup, plus model download time (varies by model size) Duration: 15-20 minutes for initial setup, plus model download time (varies by model size)
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/open-webui/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/open-webui/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->
## When to use this skill ## When to use this skill

2
skills/dgx-spark-openclaw/SKILL.md
View File

@ -16,5 +16,5 @@ Running OpenClaw and its LLMs **fully on your DGX Spark** keeps your data privat
Duration: About 30 minutes for install and first-time model setup; model download time depends on size and network (gpt-oss-120b is ~65GB and may take longer on slower connections). · Risk: **Medium to High**—the agent has access to whatever files, tools, and channels you configure. Risk increases significantly if you enable terminal/command execution skills or connect external accounts. Without proper isolation, this setup could expose sensitive data or allow code execution. **Always follow the security measures above.** Duration: About 30 minutes for install and first-time model setup; model download time depends on size and network (gpt-oss-120b is ~65GB and may take longer on slower connections). · Risk: **Medium to High**—the agent has access to whatever files, tools, and channels you configure. Risk increases significantly if you enable terminal/command execution skills or connect external accounts. Without proper isolation, this setup could expose sensitive data or allow code execution. **Always follow the security measures above.**
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/openclaw/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/openclaw/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-openshell/SKILL.md
View File

@ -19,5 +19,5 @@ By combining OpenClaw with OpenShell on DGX Spark, you get the full power of a l
**Outcome**: You will install the OpenShell CLI (`openshell`), deploy a gateway on your DGX Spark, and launch OpenClaw inside a sandboxed environment using the pre-built OpenClaw community sandbox. The sandbox enforces filesystem, network, and process isolation by default. You will also configure local inference routing so OpenClaw uses a model running on your Spark without needing external API keys. **Outcome**: You will install the OpenShell CLI (`openshell`), deploy a gateway on your DGX Spark, and launch OpenClaw inside a sandboxed environment using the pre-built OpenClaw community sandbox. The sandbox enforces filesystem, network, and process isolation by default. You will also configure local inference routing so OpenClaw uses a model running on your Spark without needing external API keys.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/openshell/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/openshell/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-portfolio-optimization/SKILL.md
View File

@ -19,5 +19,5 @@ Portfolio Optimization (PO) involves solving high-dimensional, non-linear numeri
- **Real-World Constraint Management:** Implementing constraints including concentration limits, leverage constraints, turnover limits, and cardinality constraints. - **Real-World Constraint Management:** Implementing constraints including concentration limits, leverage constraints, turnover limits, and cardinality constraints.
- **Comprehensive Backtesting:** Evaluating portfolio performance with specific tools for testing rebalancing strategies. - **Comprehensive Backtesting:** Evaluating portfolio performance with specific tools for testing rebalancing strategies.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/portfolio-optimization/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/portfolio-optimization/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-pytorch-fine-tune/SKILL.md
View File

@ -13,5 +13,5 @@ This playbook guides you through setting up and using Pytorch for fine-tuning la
**Outcome**: You'll establish a complete fine-tuning environment for large language models (1-70B parameters) on your NVIDIA Spark device. **Outcome**: You'll establish a complete fine-tuning environment for large language models (1-70B parameters) on your NVIDIA Spark device.
By the end, you'll have a working installation that supports parameter-efficient fine-tuning (PEFT) and supervised fine-tuning (SFT). By the end, you'll have a working installation that supports parameter-efficient fine-tuning (PEFT) and supervised fine-tuning (SFT).
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/pytorch-fine-tune/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/pytorch-fine-tune/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-rag-ai-workbench/SKILL.md
View File

@ -20,5 +20,5 @@ advanced RAG capabilities including query routing, response evaluation, and iter
giving you hands-on experience with both AI Workbench's development environment and sophisticated RAG giving you hands-on experience with both AI Workbench's development environment and sophisticated RAG
architectures. architectures.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/rag-ai-workbench/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/rag-ai-workbench/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-sglang/SKILL.md
View File

@ -18,5 +18,5 @@ pre-installed.
enabling high-performance LLM serving with support for text generation, chat completion, and enabling high-performance LLM serving with support for text generation, chat completion, and
vision-language tasks using models like DeepSeek-V2-Lite. vision-language tasks using models like DeepSeek-V2-Lite.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/sglang/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/sglang/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-single-cell/SKILL.md
View File

@ -20,5 +20,5 @@ This playbook shows an end-to-end GPU-powered workflow for scRNA-seq using [RAPI
6. Batch Correction and analysis using Harmony, k-nearest neighbors, UMAP, and tSNE 6. Batch Correction and analysis using Harmony, k-nearest neighbors, UMAP, and tSNE
7. Explore the biological information from the data with differential expression analysis and trajectory analysis 7. Explore the biological information from the data with differential expression analysis and trajectory analysis
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/single-cell/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/single-cell/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-spark-reachy-photo-booth/SKILL.md
View File

@ -19,5 +19,5 @@ Spark & Reachy Photo Booth is an interactive and event-driven photo booth demo t
**Outcome**: You'll deploy a complete photo booth system on DGX Spark running multiple inference models locally — LLM, image generation, speech recognition, speech generation, and computer vision — all without cloud dependencies. The Reachy robot interacts with users through natural conversation, captures photos, and generates custom images based on prompts, demonstrating real-time multimodal AI processing on edge hardware. **Outcome**: You'll deploy a complete photo booth system on DGX Spark running multiple inference models locally — LLM, image generation, speech recognition, speech generation, and computer vision — all without cloud dependencies. The Reachy robot interacts with users through natural conversation, captures photos, and generates custom images based on prompts, demonstrating real-time multimodal AI processing on edge hardware.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/spark-reachy-photo-booth/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/spark-reachy-photo-booth/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-speculative-decoding/SKILL.md
View File

@ -14,5 +14,5 @@ This way, the big model doesn't need to predict every token step-by-step, reduci
**Outcome**: You'll explore speculative decoding using TensorRT-LLM on NVIDIA Spark using two approaches: EAGLE-3 and Draft-Target. **Outcome**: You'll explore speculative decoding using TensorRT-LLM on NVIDIA Spark using two approaches: EAGLE-3 and Draft-Target.
These examples demonstrate how to accelerate large language model inference while maintaining output quality. These examples demonstrate how to accelerate large language model inference while maintaining output quality.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/speculative-decoding/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/speculative-decoding/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-tailscale/SKILL.md
View File

@ -22,5 +22,5 @@ all traffic automatically encrypted and NAT traversal handled transparently.
Duration: 15-30 minutes for initial setup, 5 minutes per additional device Duration: 15-30 minutes for initial setup, 5 minutes per additional device
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/tailscale/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/tailscale/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-trt-llm/SKILL.md
View File

@ -19,5 +19,5 @@ inference through kernel-level optimizations, efficient memory layouts, and adva
Duration: 45-60 minutes for setup and API server deployment · Risk: Medium - container pulls and model downloads may fail due to network issues Duration: 45-60 minutes for setup and API server deployment · Risk: Medium - container pulls and model downloads may fail due to network issues
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/trt-llm/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/trt-llm/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-txt2kg/SKILL.md
View File

@ -26,5 +26,5 @@ The setup includes:
Duration: - 2-3 minutes for initial setup and container deployment Duration: - 2-3 minutes for initial setup and container deployment
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/txt2kg/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/txt2kg/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-unsloth/SKILL.md
View File

@ -20,5 +20,5 @@ parameter-efficient fine-tuning methods like LoRA and QLoRA.
Duration: 30-60 minutes for initial setup and test run Duration: 30-60 minutes for initial setup and test run
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/unsloth/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/unsloth/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-vibe-coding/SKILL.md
View File

@ -26,5 +26,5 @@ You'll have a fully configured DGX Spark system capable of:
- DGX Spark (128GB unified memory recommended) - DGX Spark (128GB unified memory recommended)
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/vibe-coding/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/vibe-coding/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-vllm/SKILL.md
View File

@ -18,7 +18,7 @@ vLLM is an inference engine designed to run large language models efficiently. T
either using a pre-built Docker container or building from source with custom LLVM/Triton either using a pre-built Docker container or building from source with custom LLVM/Triton
support for ARM64. support for ARM64.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/vllm/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/vllm/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->
## When to use this skill ## When to use this skill

2
skills/dgx-spark-vscode/SKILL.md
View File

@ -16,5 +16,5 @@ This walkthrough will help you set up Visual Studio Code, a full-featured IDE wi
**Outcome**: You will have VS Code set up for development on your DGX Spark device with access to the system's ARM64 architecture and GPU resources. This setup enables direct code development, debugging, and execution. **Outcome**: You will have VS Code set up for development on your DGX Spark device with access to the system's ARM64 architecture and GPU resources. This setup enables direct code development, debugging, and execution.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/vscode/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/vscode/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->

2
skills/dgx-spark-vss/SKILL.md
View File

@ -12,5 +12,5 @@ Deploy NVIDIA's Video Search and Summarization (VSS) AI Blueprint to build intel
**Outcome**: You will deploy NVIDIA's VSS AI Blueprint on NVIDIA Spark hardware with Blackwell architecture, choosing between two deployment scenarios: VSS Event Reviewer (completely local with VLM pipeline) or Standard VSS (hybrid deployment with remote LLM/embedding endpoints). This includes setting up Alert Bridge, VLM Pipeline, Alert Inspector UI, Video Storage Toolkit, and optional DeepStream CV pipeline for automated video analysis and event review. **Outcome**: You will deploy NVIDIA's VSS AI Blueprint on NVIDIA Spark hardware with Blackwell architecture, choosing between two deployment scenarios: VSS Event Reviewer (completely local with VLM pipeline) or Standard VSS (hybrid deployment with remote LLM/embedding endpoints). This includes setting up Alert Bridge, VLM Pipeline, Alert Inspector UI, Video Storage Toolkit, and optional DeepStream CV pipeline for automated video analysis and event review.
**Full playbook**: `/Users/jkneen/Documents/GitHub/dgx-spark-playbooks/nvidia/vss/README.md` **Full playbook**: `/home/runner/work/dgx-spark-playbooks/dgx-spark-playbooks/nvidia/vss/README.md`
<!-- GENERATED:END --> <!-- GENERATED:END -->