Merge 59bedc4afe into 8452a1c5b1

2026-06-22 22:29:30 +00:00 · 2026-04-08 06:05:19 +00:00
9 changed files with 166 additions and 232 deletions
--- a/README.md
+++ b/README.md
@ -40,7 +40,7 @@ Each playbook includes prerequisites, step-by-step instructions, troubleshooting
 - [Connect Multiple DGX Spark through a Switch](nvidia/multi-sparks-through-switch/)
 - [NCCL for Two Sparks](nvidia/nccl/)
 - [Fine-tune with NeMo](nvidia/nemo-fine-tune/)
- [NemoClaw with Nemotron 3 Super and Telegram on DGX Spark](nvidia/nemoclaw/)
+- [NemoClaw with Nemotron-3-Super and Telegram on DGX Spark](nvidia/nemoclaw/)
 - [Nemotron-3-Nano with llama.cpp](nvidia/nemotron/)
 - [NIM on Spark](nvidia/nim-llm/)
 - [NVFP4 Quantization](nvidia/nvfp4-quantization/)
--- a/nvidia/llama-cpp/README.md
+++ b/nvidia/llama-cpp/README.md
@ -1,6 +1,6 @@
 # Run models with llama.cpp on DGX Spark

-> Build llama.cpp with CUDA and serve models via an OpenAI-compatible API (Nemotron 3 Nano Omni as example)
+> Build llama.cpp with CUDA and serve models via an OpenAI-compatible API (Gemma 4 31B IT as example)


 ## Table of Contents
@ -17,15 +17,15 @@

 [llama.cpp](https://github.com/ggml-org/llama.cpp) is a lightweight C/C++ inference stack for large language models. You build it with CUDA so tensor work runs on the DGX Spark GB10 GPU, then load GGUF weights and expose chat through `llama-server`’s OpenAI-compatible HTTP API.

-This playbook walks through that stack end to end using **Nemotron 3 Nano Omni** as the hands-on example: an NVIDIA MoE family that runs well from quantized GGUF on Spark. Checkpoint choices and paths for all supported models are summarized in the matrix below; commands are in the instructions.
+This playbook walks through that stack end to end. As the model example, it uses **Gemma 4 31B IT** - a frontier reasoning model built by Google DeepMind that llama.cpp supports, with strengths in coding, agentic workflows, and fine-tuning. The instructions download its **F16** GGUF from Hugging Face. The same build and server steps apply to other GGUFs (including other sizes in the support matrix below).

 ## What you'll accomplish

-You will build llama.cpp with CUDA for GB10, download a **Nemotron 3 Nano Omni** example checkpoint, and run **`llama-server`** with GPU offload. You get:
+You will build llama.cpp with CUDA for GB10, download a Gemma 4 31B IT model checkpoint, and run **`llama-server`** with GPU offload. You get:

 - Local inference through llama.cpp (no separate Python inference framework required)
 - An OpenAI-compatible `/v1/chat/completions` endpoint for tools and apps
- A concrete validation that the **Nemotron 3 Nano Omni** example runs on this stack on DGX Spark
+- A concrete validation that **Gemma 4 31B IT** runs on this stack on DGX Spark

 ## What to know before starting

@ -39,8 +39,8 @@ You will build llama.cpp with CUDA for GB10, download a **Nemotron 3 Nano Omni**
 **Hardware requirements**

 - NVIDIA DGX Spark with GB10 GPU
- Sufficient unified memory for the example **Q8_0** checkpoint (weights on the order of **~35GB**, plus KV cache and runtime overhead—scale up if you pick a larger quant or longer context)
- At least **~40GB** free disk for the example download plus build artifacts (more if you keep multiple GGUFs)
+- Sufficient unified memory for the F16 checkpoint (on the order of **~62GB** for weights alone; more when KV cache and runtime overhead are included)
+- At least **~70GB** free disk for the F16 download plus build artifacts (use a smaller quant from the same repo if you need less disk and VRAM)

 **Software requirements**

@ -50,15 +50,12 @@ You will build llama.cpp with CUDA for GB10, download a **Nemotron 3 Nano Omni**
 - CUDA Toolkit: `nvcc --version`
 - Network access to GitHub and Hugging Face

-## Model support matrix
+## Model Support Matrix

-The following models are supported with llama.cpp on Spark. The instructions use the **Nemotron 3 Nano Omni** example row by default.
+The following models are supported with llama.cpp on Spark. All listed models are available and ready to use:

 | Model | Support Status | HF Handle |
 |-------|----------------|-----------|
-| **Nemotron 3 Nano Omni** (example walkthrough) | ✅ | `ggml-org/NVIDIA-Nemotron-3-Nano-Omni` |
-| **Qwen3.6-35B-A3B** | ✅ | `unsloth/Qwen3.6-35B-A3B-GGUF` |
-| **Qwen3.6-27B** | ✅ | `unsloth/Qwen3.6-27B-GGUF` |
 | **Gemma 4 31B IT** | ✅ | `ggml-org/gemma-4-31B-it-GGUF` |
 | **Gemma 4 26B A4B IT** | ✅ | `ggml-org/gemma-4-26B-A4B-it-GGUF` |
 | **Gemma 4 E4B IT** | ✅ | `ggml-org/gemma-4-E4B-it-GGUF` |
@ -67,17 +64,17 @@ The following models are supported with llama.cpp on Spark. The instructions use

 ## Time & risk

-* **Estimated time:** About 30 minutes, plus downloading the example GGUF (~35GB order of magnitude for the default quant)
+* **Estimated time:** About 30 minutes, plus downloading the ~62GB example 
 * **Risk level:** Low — build is local to your clone; no system-wide installs required for the steps below
 * **Rollback:** Remove the `llama.cpp` clone and the model directory under `~/models/` to reclaim disk space
-* **Last updated:** 04/28/2026
-  * Walkthrough now uses Nemotron Omni; other model rows stay available
+* **Last updated:** 04/02/2026
+  * First Publication

 ## Instructions

 ## Step 1. Verify prerequisites

-The **example** checkpoint is **`nemotron-3-nano-omni-ga_v1.0-Q8_0.gguf`** from Hugging Face repo **`ggml-org/NVIDIA-Nemotron-3-Nano-Omni`** (full handle: `ggml-org/NVIDIA-Nemotron-3-Nano-Omni/nemotron-3-nano-omni-ga_v1.0-Q8_0.gguf`). Other supported GGUFs—including Qwen3.6, Gemma, and alternate Nemotron Omni builds—use the same build and server steps; change `hf download` and `--model` paths (see the [overview model matrix](overview.md)).
+This walkthrough uses **Gemma 4 31B IT** (`gemma-4-31B-it-f16.gguf`) as the example checkpoint. You can substitute another GGUF from [`ggml-org/gemma-4-31B-it-GGUF`](https://huggingface.co/ggml-org/gemma-4-31B-it-GGUF) (for example `Q4_K_M` or `Q8_0`) by changing the `hf download` filename and `--model` path in later steps.

 Ensure the required tools are installed:

@ -124,25 +121,25 @@ make -j8

 The build usually takes on the order of 5–10 minutes. When it finishes, binaries such as `llama-server` appear under `build/bin/`.

-## Step 4. Download example Nemotron 3 Nano Omni GGUF
+## Step 4. Download Gemma 4 31B IT GGUF (supported model example)

-llama.cpp loads models in **GGUF** format. This playbook uses the **Q8_0** checkpoint from `ggml-org/NVIDIA-Nemotron-3-Nano-Omni`, which balances quality and memory on DGX Spark GB10 unified memory.
+llama.cpp loads models in **GGUF** format. **gemma-4-31B-it** is available in GGUF from Hugging Face; this playbook uses a F16 variant that balances quality and memory on GB10-class hardware.

 ```bash
-hf download ggml-org/NVIDIA-Nemotron-3-Nano-Omni \
-  nemotron-3-nano-omni-ga_v1.0-Q8_0.gguf \
-  --local-dir ~/models/NVIDIA-Nemotron-3-Nano-Omni
+hf download ggml-org/gemma-4-31B-it-GGUF \
+  gemma-4-31B-it-f16.gguf \
+  --local-dir ~/models/gemma-4-31B-it-GGUF
 ```

-The file is on the order of **~35GB** (exact size may vary). The download can be resumed if interrupted.
+The F16 file is large (**~62GB**). The download can be resumed if interrupted.

-## Step 5. Start llama-server with Nemotron 3 Nano Omni
+## Step 5. Start llama-server with Gemma 4 31B IT

 From your `llama.cpp/build` directory, launch the OpenAI-compatible server with GPU offload:

 ```bash
 ./bin/llama-server \
-  --model ~/models/NVIDIA-Nemotron-3-Nano-Omni/nemotron-3-nano-omni-ga_v1.0-Q8_0.gguf \
+  --model ~/models/gemma-4-31B-it-GGUF/gemma-4-31B-it-f16.gguf \
  --host 0.0.0.0 \
  --port 30000 \
  --n-gpu-layers 99 \
@ -165,7 +162,7 @@ llama_new_context_with_model: n_ctx = 8192
 main: server is listening on 0.0.0.0:30000
 ```

-**Keep this terminal open** while testing. Large GGUFs can take a minute or more to load; until you see `server is listening`, nothing accepts connections on port 30000 (see Troubleshooting if `curl` reports connection refused).
+**Keep this terminal open** while testing. Large GGUFs can take several minutes to load; until you see `server is listening`, nothing accepts connections on port 30000 (see Troubleshooting if `curl` reports connection refused).

 ## Step 6. Test the API

@ -175,7 +172,7 @@ Use a **second terminal on the same machine** that runs `llama-server` (for exam
 curl -X POST http://127.0.0.1:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
-    "model": "nemotron",
+    "model": "gemma4",
    "messages": [{"role": "user", "content": "New York is a great city because..."}],
    "max_tokens": 100
  }'
@ -198,7 +195,7 @@ Example shape of the response (fields vary by llama.cpp version; `message` may i
    }
  ],
  "created": 1765916539,
-  "model": "nemotron-3-nano-omni-ga_v1.0-Q8_0.gguf",
+  "model": "gemma-4-31B-it-f16.gguf",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 100,
@ -212,15 +209,15 @@ Example shape of the response (fields vary by llama.cpp version; `message` may i
 }
 ```

-## Step 7. Longer completion (with Nemotron 3 Nano Omni)
+## Step 7. Longer completion (with example model)

-Try a slightly longer prompt to confirm stable generation with **Nemotron 3 Nano Omni**:
+Try a slightly longer prompt to confirm stable generation with **Gemma 4 31B IT**:

 ```bash
 curl -X POST http://127.0.0.1:30000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
-    "model": "nemotron",
+    "model": "gemma4",
    "messages": [{"role": "user", "content": "Solve this step by step: If a train travels 120 miles in 2 hours, what is its average speed?"}],
    "max_tokens": 500
  }'
@ -234,7 +231,7 @@ To remove this tutorial’s artifacts:

 ```bash
 rm -rf ~/llama.cpp
-rm -rf ~/models/NVIDIA-Nemotron-3-Nano-Omni
+rm -rf ~/models/gemma-4-31B-it-GGUF
 ```

 Deactivate the Python venv if you no longer need `hf`:
--- a/nvidia/lm-studio/README.md
+++ b/nvidia/lm-studio/README.md
@ -27,7 +27,7 @@ This playbook shows you how to deploy LM Studio on an NVIDIA DGX Spark device to

 ## What you'll accomplish

-You'll deploy LM Studio on an NVIDIA DGX Spark device to run **Nemotron 3 Nano Omni** (`nvidia/nemotron-3-nano-omni`), and use the model from your laptop. More specifically, you will:
+You'll deploy LM Studio on an NVIDIA DGX Spark device to run gpt-oss 120B, and use the model from your laptop. More specifically, you will:

 - Install **llmster**, a totally headless, terminal native LM Studio on the Spark
 - Run LLM inference locally on DGX Spark via API
@ -54,15 +54,6 @@ You'll deploy LM Studio on an NVIDIA DGX Spark device to run **Nemotron 3 Nano O
 - Laptop and DGX Spark must be on the same local network
 - Network access to download packages and models

-## Model support matrix
-To explore all supported models in LM Studio, check out [LM Studio model catalog](https://lmstudio.ai/models) page.
-
-| Model | Support Status | Model Path |
-|-------|----------------|-----------|
-| **Nemotron 3 Nano Omni** | ✅ | `nvidia/nemotron-3-nano-omni` |
-| **Qwen3.6-35B-A3B** | ✅ | `qwen/qwen3.6-35b-a3b` |
-| **GPT-OSS-120B** | ✅ | `openai/gpt-oss-120b` |
-
 ## LM Link (optional)

 [LM Link](https://lmstudio.ai/link) lets you **use your local models remotely**. You link machines (e.g. your DGX Spark and your laptop), then load models on the Spark and use them from the laptop as if they were local.
@ -75,7 +66,7 @@ If you use LM Link, you can skip binding the server to `0.0.0.0` and using the S

 ## Ancillary files

-All required assets can be found below. These sample scripts can be used in Step 7 of Instructions.
+All required assets can be found below. These sample scripts can be used in Step 6 of Instructions.

 - [run.js](https://github.com/lmstudio-ai/docs/blob/main/_assets/nvidia-spark-playbook/js/run.js) - JavaScript script for sending a test prompt to Spark
 - [run.py](https://github.com/lmstudio-ai/docs/blob/main/_assets/nvidia-spark-playbook/py/run.py) - Python script for sending a test prompt to Spark
@ -89,8 +80,8 @@ All required assets can be found below. These sample scripts can be used in Step
 * **Rollback:**
  * Downloaded models can be removed manually from the models directory.
  * Uninstall LM Studio or llmster
-* **Last Updated:** 04/28/2026
-  * Introduce Nemotron Omni as example
+* **Last Updated:** 03/12/2026
+  * Add instructions for LM Link features

 ## Instructions

@ -147,22 +138,22 @@ where `<SPARK_IP>` is your device's IP address. You can find your Spark’s IP a
 hostname -I
 ```

-## Step 4. (Optional) Connect with LM Link
+## Step 3b. (Optional) Connect with LM Link

 **LM Link** lets you use your Spark’s models from your laptop (or other devices) as if they were local, over an end-to-end encrypted connection. You don’t need to be on the same local network or bind the server to `0.0.0.0`.

 1. **Create a Link** — Go to [lmstudio.ai/link](https://lmstudio.ai/link) and follow **Create your Link** to set up your private LM Link network.
 2. **Link both devices** — On your DGX Spark (llmster) and on your laptop, sign in and join the same Link. LM Link uses Tailscale mesh VPNs; devices communicate without opening ports to the internet.
-3. **Use remote models** — On your laptop, open LM Studio (or use the local server). Remote models from your Spark appear in the model loader. Any tool that connects to `localhost:1234` — including the LM Studio SDK, Codex, Claude Code, OpenCode, and the scripts in Step 7 — can use those models without changing the endpoint.
+3. **Use remote models** — On your laptop, open LM Studio (or use the local server). Remote models from your Spark appear in the model loader. Any tool that connects to `localhost:1234` — including the LM Studio SDK, Codex, Claude Code, OpenCode, and the scripts in Step 6 — can use those models without changing the endpoint.

 LM Link is in **Preview** and is free for up to 2 users, 5 devices each. For details and limits, see [LM Link](https://lmstudio.ai/link).

-## Step 5. Download a model to your Spark
+## Step 4. Download a model to your Spark

-As an example, download **NVIDIA Nemotron 3 Nano Omni** from the LM Studio catalog (`nvidia/nemotron-3-nano-omni`) so you can run it on Spark with plenty of unified memory.
+As an example, let's download and run gpt-oss 120B, one of the best open source models from OpenAI. This model is too large for many laptops due to memory limitations, which makes this a fantastic use case for the Spark.

 ```bash
-lms get nvidia/nemotron-3-nano-omni
+lms get openai/gpt-oss-120b
 ```

 This download will take a while due to its large size. Verify that the model has been successfully downloaded by listing your models:
@ -171,15 +162,15 @@ This download will take a while due to its large size. Verify that the model has
 lms ls
 ```

-## Step 6. Load the model 
+## Step 5. Load the model 

 Load the model on your Spark so that it is ready to respond to requests from your laptop.

 ```bash
-lms load nvidia/nemotron-3-nano-omni
+lms load openai/gpt-oss-120b
 ```

-## Step 7. Set up a simple program that uses LM Studio SDK on the laptop
+## Step 6. Set up a simple program that uses LM Studio SDK on the laptop

 Install the LM Studio SDKs and use a simple script to send a prompt to your Spark and validate the response. To get started quickly, we provide simple scripts below for Python, JavaScript, and Bash. Download the scripts from the Overview page of this playbook and run the corresponding command from the directory containing it.

@ -211,12 +202,12 @@ Pre-reqs: User has installed `jq` and `curl`
 bash run.sh
 ```

-## Step 8. Next Steps
+## Step 7. Next Steps

 - Try downloading and serving different models from the [LM Studio model catalog](https://lmstudio.ai/models).
 - Use [LM Link](https://lmstudio.ai/link) to connect more devices and use your Spark’s models from anywhere with end-to-end encryption.

-## Step 9. Cleanup and rollback
+## Step 8. Cleanup and rollback
 Remove and uninstall LM Studio completely if needed. Note that LM Studio stores models separately from the application. Uninstalling LM Studio will not remove downloaded models unless you explicitly delete them.

 If you want to remove the entire LM Studio application, quit LM Studio from the tray first, then move the application to trash.
--- a/nvidia/nemoclaw/README.md
+++ b/nvidia/nemoclaw/README.md
@ -1,4 +1,4 @@
-# NemoClaw with Nemotron 3 Super and Telegram on DGX Spark
+# NemoClaw with Nemotron-3-Super and Telegram on DGX Spark

 > Install NemoClaw on DGX Spark with local Ollama inference and Telegram bot integration

@ -25,8 +25,8 @@
  - [Step 6. Talk to the agent (CLI)](#step-6-talk-to-the-agent-cli)
  - [Step 7. Interactive TUI](#step-7-interactive-tui)
  - [Step 8. Exit the sandbox and access the Web UI](#step-8-exit-the-sandbox-and-access-the-web-ui)
-  - [Step 9. Create a Telegram bot](#step-9-create-a-telegram-bot)
-  - [Step 10. Install cloudflared and start the Telegram bridge](#step-10-install-cloudflared-and-start-the-telegram-bridge)
+  - [Step 9. Prepare credentials](#step-9-prepare-credentials)
+  - [Step 10. Configure and start the Telegram bridge](#step-10-configure-and-start-the-telegram-bridge)
  - [Step 11. Stop services](#step-11-stop-services)
  - [Step 12. Uninstall NemoClaw](#step-12-uninstall-nemoclaw)
 - [Troubleshooting](#troubleshooting)
@ -97,7 +97,8 @@ By participating in this demo, you acknowledge that you are solely responsible f
 **Hardware and access:**

 - A DGX Spark (GB10) with keyboard and monitor, or SSH access
- A **Telegram bot token** from [@BotFather](https://t.me/BotFather) (create one with `/newbot`) -- only needed if you want the Telegram bot. Have it ready *before* running the installer; the onboard wizard prompts for it.
+- An **NVIDIA API key** from [build.nvidia.com](https://build.nvidia.com/settings/api-keys) (needed for the Telegram bridge)
+- A **Telegram bot token** from [@BotFather](https://t.me/BotFather) (create one with `/newbot`)

 **Software:**

@ -117,7 +118,8 @@ Expected: Ubuntu 24.04, NVIDIA GB10 GPU, Docker 28.x+.

 | Item | Where to get it |
 |------|----------------|
-| Telegram bot token (optional) | [@BotFather](https://t.me/BotFather) on Telegram -- create with `/newbot`. Required only for the Telegram bot; have it ready before running the installer. |
+| NVIDIA API key | [build.nvidia.com/settings/api-keys](https://build.nvidia.com/settings/api-keys) |
+| Telegram bot token | [@BotFather](https://t.me/BotFather) on Telegram -- create with `/newbot` |

 ### Ancillary files

@ -127,8 +129,8 @@ All required assets are handled by the NemoClaw installer. No manual cloning is

 - **Estimated time:** 20--30 minutes (with Ollama and model already downloaded). First-time model download adds ~15--30 minutes depending on network speed.
 - **Risk level:** Medium -- you are running an AI agent in a sandbox; risks are reduced by isolation but not eliminated. Use a clean environment and do not connect sensitive data or production accounts.
- **Last Updated:** 04/28/2026
-  * Updated for NemoClaw v0.0.22+: revised Telegram setup, renamed tunnel commands, refreshed uninstall instructions.
+- **Last Updated:** 03/31/2026
+  * First Publication

 ## Instructions

@ -190,6 +192,14 @@ Install Ollama:
 curl -fsSL https://ollama.com/install.sh | sh
 ```

+Verify it is running:
+
+```bash
+curl http://localhost:11434
+```
+
+Expected: `Ollama is running`. If not, start it: `ollama serve &`
+
 Configure Ollama to listen on all interfaces so the sandbox container can reach it:

 ```bash
@ -199,17 +209,6 @@ sudo systemctl daemon-reload
 sudo systemctl restart ollama
 ```

-Verify it is running and reachable on all interfaces:
-
-```bash
-curl http://0.0.0.0:11434
-```
-
-Expected: `Ollama is running`. If not, start it with `sudo systemctl start ollama`.
-
-> [!IMPORTANT]
-> Always start Ollama via systemd (`sudo systemctl restart ollama`) — do not use `ollama serve &`. A manually started Ollama process does not pick up the `OLLAMA_HOST=0.0.0.0` setting above, and the NemoClaw sandbox will not be able to reach the inference server.
-
 ### Step 3. Pull the Nemotron 3 Super model

 Download Nemotron 3 Super 120B (~87 GB; may take 15--30 minutes depending on network speed):
@ -238,22 +237,18 @@ You should see `nemotron-3-super:120b` in the output.

 ### Step 4. Install NemoClaw

-This single command handles everything: installs Node.js (if needed), installs OpenShell, clones the latest stable NemoClaw release, builds the CLI, and runs the onboard wizard to create a sandbox.
+This single command handles everything: installs Node.js (if needed), installs OpenShell, clones NemoClaw at the pinned stable release (`v0.0.1`), builds the CLI, and runs the onboard wizard to create a sandbox.

 ```bash
-curl -fsSL https://www.nvidia.com/nemoclaw.sh | bash
+curl -fsSL https://www.nvidia.com/nemoclaw.sh | NEMOCLAW_INSTALL_TAG=v0.0.4 bash
 ```

 The onboard wizard walks you through setup:

 1. **Sandbox name** -- Pick a name (e.g. `my-assistant`). Names must be lowercase alphanumeric with hyphens only.
-2. **Inference provider** -- Select **Local Ollama**.
-3. **Model** -- Select **nemotron-3-super:120b**.
-4. **Messaging channels** -- If you want a Telegram bot, select `telegram` here and paste your bot token when prompted. Create the bot first via [@BotFather](https://t.me/BotFather) in Telegram (see Step 9). If you skip this, you can re-run the installer later to recreate the sandbox with Telegram enabled.
-5. **Policy presets** -- Accept the suggested presets when prompted (hit **Y**).
-
-> [!IMPORTANT]
-> Telegram must be configured at this step. The channel plugin and bot token are wired into the sandbox container during onboarding — they cannot be added to an existing sandbox by exporting environment variables on the host.
+2. **Inference provider** -- Select **Local Ollama** (option 7).
+3. **Model** -- Select **nemotron-3-super:120b** (option 1).
+4. **Policy presets** -- Accept the suggested presets when prompted (hit **Y**).

 When complete you will see output like:

@ -299,7 +294,7 @@ Expected: JSON listing `nemotron-3-super:120b`.
 Still inside the sandbox, send a test message:

 ```bash
-openclaw agent --agent main -m "hello" --session-id test
+openclaw agent --agent main --local -m "hello" --session-id test
 ```

 The agent will respond using Nemotron 3 Super. First responses may take 30--90 seconds for a 120B parameter model running locally.
@ -328,7 +323,7 @@ exit
 http://127.0.0.1:18789/#token=<long-token-here>
 ```

-**If accessing the Web UI from a remote machine**, you need to set up an SSH tunnel. The NemoClaw onboard wizard already created the port 18789 forward on the Spark, so you only need to tunnel from your remote machine.
+**If accessing the Web UI from a remote machine**, you need to set up port forwarding.

 First, find your Spark's IP address. On the Spark, run:

@ -338,7 +333,13 @@ hostname -I | awk '{print $1}'

 This prints the primary IP address (e.g. `192.168.1.42`). You can also find it in **Settings > Wi-Fi** or **Settings > Network** on the Spark's desktop, or check your router's connected-devices list.

-From your remote machine, create an SSH tunnel to the Spark (replace `<your-spark-ip>` with the IP address from above):
+Start the port forward on the Spark host:
+
+```bash
+openshell forward start 18789 my-assistant --background
+```
+
+Then from your remote machine, create an SSH tunnel to the Spark (replace `<your-spark-ip>` with the IP address from above):

 ```bash
 ssh -L 18789:127.0.0.1:18789 <your-user>@<your-spark-ip>
@ -353,70 +354,64 @@ http://127.0.0.1:18789/#token=<long-token-here>
 > [!IMPORTANT]
 > Use `127.0.0.1`, not `localhost` -- the gateway origin check requires an exact match.

-> [!NOTE]
-> If the Web UI fails to load and the port forward may be stale, reset it on the Spark host:
-> ```bash
-> openshell forward stop 18789 my-assistant || true
-> openshell forward start 18789 my-assistant --background
-> ```
-
 ---

 ## Phase 3: Telegram Bot

-> [!IMPORTANT]
-> Telegram must be enabled in the **NemoClaw onboard wizard** (Step 4 → Messaging channels). The channel plugin and bot token are wired into the sandbox container at sandbox creation time — `policy-add` only opens network egress and is not enough on its own. If you skipped Telegram during onboard, re-run the installer to recreate the sandbox with Telegram enabled.
+### Step 9. Prepare credentials

-### Step 9. Create a Telegram bot
+You need two items:

-Do this **before** running the NemoClaw installer in Step 4 so you have your bot token ready when the wizard prompts for it.
+| Item | Where to get it |
+|------|----------------|
+| Telegram bot token | Open Telegram, find [@BotFather](https://t.me/BotFather), send `/newbot`, and follow the prompts. Copy the token it gives you. |
+| NVIDIA API key | Go to [build.nvidia.com/settings/api-keys](https://build.nvidia.com/settings/api-keys) and create or copy a key (starts with `nvapi-`). |

-Open Telegram, find [@BotFather](https://t.me/BotFather), send `/newbot`, and follow the prompts. Copy the bot token it gives you and paste it into the wizard when you reach the **Messaging channels** step.
-
-### Step 10. Install cloudflared and start the Telegram bridge
-
-The Telegram bridge needs a public webhook URL so Telegram can deliver messages to your bot. NemoClaw uses [cloudflared](https://developers.cloudflare.com/cloudflare-one/connections/connect-networks/) to create a free `trycloudflare.com` tunnel.
+### Step 10. Configure and start the Telegram bridge

 Make sure you are on the **host** (not inside the sandbox). If you are inside the sandbox, run `exit` first.

-Install cloudflared (DGX Spark is arm64):
+Set the required environment variables. Replace the placeholders with your actual values. `SANDBOX_NAME` must match the sandbox name you chose during the onboard wizard:

 ```bash
-curl -L --output cloudflared.deb \
-  https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-arm64.deb
-sudo dpkg -i cloudflared.deb
+export TELEGRAM_BOT_TOKEN=<your-bot-token>
+export SANDBOX_NAME=my-assistant
 ```

-Start the tunnel:
+Add the Telegram network policy to the sandbox:

 ```bash
-nemoclaw tunnel start
+nemoclaw my-assistant policy-add
 ```

-Verify the public URL is live:
+When prompted, type `telegram` and hit **Y** to confirm.
+
+Start the Telegram bridge. On first run it will ask for your NVIDIA API key:

 ```bash
-nemoclaw status
+nemoclaw start
 ```

-You should see `● cloudflared` with a `trycloudflare.com` public URL (e.g. `https://assembled-peer-persian-kitty.trycloudflare.com`).
+Paste your `nvapi-` key when prompted.
+
+You should see:
+
+```text
+[services] telegram-bridge started
+Telegram:    bridge running
+```

 Open Telegram, find your bot, and send it a message. The bot forwards it to the agent and replies.

 > [!NOTE]
-> If `nemoclaw tunnel start` prints `cloudflared not found — no public URL`, the cloudflared install above did not complete successfully. Re-run the install, then restart the tunnel:
+> The first response may include a debug log line like "gateway Running as non-root..." -- this is cosmetic and can be ignored.
+
+> [!NOTE]
+> If you need to restart the bridge, `nemoclaw stop` may not cleanly stop the process. If that happens, find and kill the bridge process via its PID file:
 > ```bash
-> nemoclaw tunnel stop && nemoclaw tunnel start
+> kill -9 "$(cat /tmp/nemoclaw-services-${SANDBOX_NAME}/telegram-bridge.pid)"
 > ```
-
-> [!NOTE]
-> The first response may take 30--90 seconds for a 120B parameter model running locally.
-
-> [!NOTE]
-> If sending a message returns `Error: Channel is unavailable: telegram`, the channel was not enabled during onboard. Re-run the installer to recreate the sandbox with Telegram selected at the **Messaging channels** step.
-
-> [!NOTE]
-> For details on restricting which Telegram chats can interact with the agent, see the [NemoClaw Telegram bridge documentation](https://docs.nvidia.com/nemoclaw/latest/deployment/set-up-telegram-bridge.html).
+> Then run `nemoclaw start` again.

 ---

@ -424,10 +419,10 @@ Open Telegram, find your bot, and send it a message. The bot forwards it to the

 ### Step 11. Stop services

-Stop the cloudflared tunnel:
+Stop any running auxiliary services (Telegram bridge, cloudflared):

 ```bash
-nemoclaw tunnel stop
+nemoclaw stop
 ```

 Stop the port forward:
@ -439,13 +434,14 @@ openshell forward stop 18789    # stop the dashboard forward

 ### Step 12. Uninstall NemoClaw

-Run the uninstaller via curl (matches the [NemoClaw README](https://github.com/NVIDIA/NemoClaw)). It removes all sandboxes, the OpenShell gateway, Docker containers/images/volumes, the CLI, and all state files. Docker, Node.js, npm, and Ollama are preserved.
+Run the uninstaller from the cloned source directory. It removes all sandboxes, the OpenShell gateway, Docker containers/images/volumes, the CLI, and all state files. Docker, Node.js, npm, and Ollama are preserved.

 ```bash
-curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh | bash
+cd ~/.nemoclaw/source
+./uninstall.sh
 ```

-**Uninstaller flags** (pass via `bash -s -- <flags>`):
+**Uninstaller flags:**

 | Flag | Effect |
 |------|--------|
@ -453,10 +449,10 @@ curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uni
 | `--keep-openshell` | Leave the `openshell` binary in place |
 | `--delete-models` | Also remove the Ollama models pulled by NemoClaw |

-To remove everything including the Ollama model, non-interactively:
+To remove everything including the Ollama model:

 ```bash
-curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh | bash -s -- --yes --delete-models
+./uninstall.sh --yes --delete-models
 ```

 The uninstaller runs 6 steps:
@ -468,7 +464,7 @@ The uninstaller runs 6 steps:
 6. Remove state directories (`~/.nemoclaw`, `~/.config/openshell`, `~/.config/nemoclaw`) and the OpenShell binary

 > [!NOTE]
-> If you have a local clone at `~/.nemoclaw/source` you want to keep, move or back it up before running the uninstaller — it is removed as part of state cleanup in step 6.
+> The source clone at `~/.nemoclaw/source` is removed as part of state cleanup in step 6. If you want to keep a local copy, move or back it up before running the uninstaller.

 ## Useful commands

@ -478,13 +474,13 @@ The uninstaller runs 6 steps:
 | `nemoclaw my-assistant status` | Show sandbox status and inference config |
 | `nemoclaw my-assistant logs --follow` | Stream sandbox logs in real time |
 | `nemoclaw list` | List all registered sandboxes |
-| `nemoclaw tunnel start` | Start cloudflared tunnel (public URL for Telegram webhooks) |
-| `nemoclaw tunnel stop` | Stop the cloudflared tunnel |
+| `nemoclaw start` | Start auxiliary services (Telegram bridge) |
+| `nemoclaw stop` | Stop auxiliary services |
 | `openshell term` | Open the monitoring TUI on the host |
 | `openshell forward list` | List active port forwards |
 | `openshell forward start 18789 my-assistant --background` | Restart port forwarding for Web UI |
-| `curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh \| bash` | Remove NemoClaw (preserves Docker, Node.js, Ollama) |
-| `curl -fsSL https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh \| bash -s -- --delete-models` | Remove NemoClaw and Ollama models |
+| `cd ~/.nemoclaw/source && ./uninstall.sh` | Remove NemoClaw (preserves Docker, Node.js, Ollama) |
+| `cd ~/.nemoclaw/source && ./uninstall.sh --delete-models` | Remove NemoClaw and Ollama models |

 ## Troubleshooting

--- a/nvidia/openshell/README.md
+++ b/nvidia/openshell/README.md
@ -214,22 +214,34 @@ Verify Ollama is running (it auto-starts as a service after installation). If no
 ollama serve &
 ```

-Configure Ollama to listen on all interfaces so the OpenShell gateway container can reach it:
+Configure Ollama to listen on all interfaces so the OpenShell gateway container can reach it. Create a systemd override:
+
+```bash
+mkdir -p /etc/systemd/system/ollama.service.d/
+sudo nano /etc/systemd/system/ollama.service.d/override.conf
+```
+
+Add these lines to the file (create the file if it does not exist):
+
+```ini
+[Service]
+Environment="OLLAMA_HOST=0.0.0.0"
+```
+
+Save and exit, then reload and restart Ollama:

 ```bash
-sudo mkdir -p /etc/systemd/system/ollama.service.d
-printf '[Service]\nEnvironment="OLLAMA_HOST=0.0.0.0"\n' | sudo tee /etc/systemd/system/ollama.service.d/override.conf
 sudo systemctl daemon-reload
 sudo systemctl restart ollama
 ```

-Verify Ollama is running and reachable on all interfaces:
+Verify Ollama is listening on all interfaces:

 ```bash
-curl http://0.0.0.0:11434
+ss -tlnp | grep 11434
 ```

-Expected: `Ollama is running`. If not, start it with `sudo systemctl start ollama`.
+You should see `*:11434` in the output. If it only shows `127.0.0.1:11434`, confirm the override file contents and that you ran `systemctl daemon-reload` before restarting.

 Next, run a model from Ollama (adjust the model name to match your choice from [the Ollama model library](https://ollama.com/library)). The `ollama run` command will pull the model automatically if it is not already present. Running the model here ensures it is loaded and ready when you use it with OpenClaw, reducing the chance of timeouts later. Example for nemotron-3-super:

--- a/nvidia/sglang/README.md
+++ b/nvidia/sglang/README.md
@ -53,7 +53,6 @@ The following models are supported with SGLang on Spark. All listed models are a

 | Model | Quantization | Support Status | HF Handle |
 |-------|-------------|----------------|-----------|
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | BF16 | ✅ | [`nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16`](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16) |
 | **GPT-OSS-20B** | MXFP4 | ✅ | `openai/gpt-oss-20b` |
 | **GPT-OSS-120B** | MXFP4 | ✅ | `openai/gpt-oss-120b` |
 | **Llama-3.1-8B-Instruct** | FP8 | ✅ | `nvidia/Llama-3.1-8B-Instruct-FP8` |
@ -76,19 +75,12 @@ Note: for NVFP4 models, add the `--quantization modelopt_fp4` flag.
 * **Estimated time:** 30 minutes for initial setup and validation
 * **Risk level:** Low - Uses pre-built, validated SGLang container with minimal configuration
 * **Rollback:** Stop and remove containers with `docker stop` and `docker rm` commands
-* **Last Updated:** 04/28/2026
-    * Introduce Nemotron-3-Nano-Omni reasoning FP8 support
+* **Last Updated:** 03/15/2026
+    * Use latest NGC SGLang container: nvcr.io/nvidia/sglang:26.02-py3

 ## Instructions

-## Step 1. Use model specific deployment guide
-
-Certain models require special deployment configurations. Please refer to their respective model cards to run on DGX Spark:
-| Model | Quantization | HF Model Card Link |
-|-------|-------------|----------------|
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | BF16 | https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
-
-## Step 2. Verify system prerequisites
+## Step 1. Verify system prerequisites

 Check that your NVIDIA Spark device meets all requirements before proceeding. This step runs on
 your host system and ensures Docker, GPU drivers, and container toolkit are properly configured. 
@ -116,7 +108,7 @@ sudo usermod -aG docker $USER
 newgrp docker
 ```

-## Step 3. Pull the SGLang Container
+## Step 2. Pull the SGLang Container

 Download the latest SGLang container. This step runs on the host and may take
 several minutes depending on your network connection.
@ -130,7 +122,7 @@ docker pull nvcr.io/nvidia/sglang:26.02-py3
 docker images | grep sglang
 ```

-## Step 4. Launch SGLang container for server mode
+## Step 3. Launch SGLang container for server mode

 Start the SGLang container in server mode to enable HTTP API access. This runs the inference
 server inside the container, exposing it on port 30000 for client connections.
@ -144,7 +136,7 @@ docker run --gpus all -it --rm \
  bash
 ```

-## Step 5. Start the SGLang inference server
+## Step 4. Start the SGLang inference server

 Inside the container, launch the HTTP inference server with a supported model. This step runs
 inside the Docker container and starts the SGLang server daemon.
@ -167,7 +159,7 @@ sleep 30
 curl http://localhost:30000/health
 ```

-## Step 6. Test client-server inference
+## Step 5. Test client-server inference

 From a new terminal on your host system, test the SGLang server API to ensure it's working
 correctly. This validates that the server is accepting requests and generating responses.
@ -185,7 +177,7 @@ curl -X POST http://localhost:30000/generate \
  }'
 ```

-## Step 7. Test Python client API
+## Step 6. Test Python client API

 Create a simple Python script to test programmatic access to the SGLang server. This runs on
 the host system and demonstrates how to integrate SGLang into applications.
@ -205,7 +197,7 @@ response = requests.post('http://localhost:30000/generate', json={
 print(f"Response: {response.json()['text']}")
 ```

-## Step 8. Validate installation
+## Step 7. Validate installation

 Confirm that both server and offline modes are working correctly. This step verifies the
 complete SGLang setup and ensures reliable operation.
@ -221,7 +213,7 @@ docker ps
 docker logs <CONTAINER_ID>
 ```

-## Step 9. Cleanup and rollback
+## Step 8. Cleanup and rollback

 Stop and remove containers to clean up resources. This step returns your system to its
 original state.
@ -240,7 +232,7 @@ docker container prune -f
 docker rmi nvcr.io/nvidia/sglang:26.02-py3
 ```

-## Step 10. Next steps
+## Step 9. Next steps

 With SGLang successfully deployed, you can now:

--- a/nvidia/speculative-decoding/README.md
+++ b/nvidia/speculative-decoding/README.md
@ -57,7 +57,7 @@ In short: two Sparks let you run models that are too large for one, while specul
 - Docker with GPU support enabled

  ```bash
-  docker run --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc12 nvidia-smi
+  docker run --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 nvidia-smi
  ```
 - Active HuggingFace Token for model access
 - Network connectivity for model downloads
@ -68,9 +68,9 @@ In short: two Sparks let you run models that are too large for one, while specul
 * **Duration:** 10-20 minutes for setup, additional time for model downloads (varies by network speed)
 * **Risks:** GPU memory exhaustion with large models, container registry access issues, network timeouts during downloads
 * **Rollback:** Stop Docker containers and optionally clean up downloaded model cache.
-* **Last Updated:** 04/20/2026
-  * Upgrade to latest container 1.3.0rc12
-  * Add Speculative Decoding example with Qwen3-235B-A22B on Two Sparks
+* **Last Updated:** 01/02/2026
+  * Upgrade to latest container v1.2.0rc6
+  * Add EAGLE-3 Speculative Decoding example with GPT-OSS-120B

 ## Instructions

@ -111,7 +111,7 @@ docker run \
  -v $HOME/.cache/huggingface/:/root/.cache/huggingface/ \
  --rm -it --ulimit memlock=-1 --ulimit stack=67108864 \
  --gpus=all --ipc=host --network host \
-  nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc12 \
+  nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 \
  bash -c '
    hf download openai/gpt-oss-120b && \
    hf download nvidia/gpt-oss-120b-Eagle3-long-context \
@ -172,7 +172,7 @@ docker run \
  -e HF_TOKEN=$HF_TOKEN \
  -v $HOME/.cache/huggingface/:/root/.cache/huggingface/ \
  --rm -it --ulimit memlock=-1 --ulimit stack=67108864 \
-  --gpus=all --ipc=host --network host nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc12 \
+  --gpus=all --ipc=host --network host nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 \
  bash -c "
 #    # Download models
    hf download nvidia/Llama-3.3-70B-Instruct-FP4 && \
@ -309,7 +309,7 @@ docker run -d --rm \
  -e TRITON_PTXAS_PATH="/usr/local/cuda/bin/ptxas" \
  -v ~/.cache/huggingface/:/root/.cache/huggingface/ \
  -v ~/.ssh:/tmp/.ssh:ro \
-  nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc12 \
+  nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 \
  bash -c "curl https://raw.githubusercontent.com/NVIDIA/dgx-spark-playbooks/refs/heads/main/nvidia/trt-llm/assets/trtllm-mn-entrypoint.sh | bash"
 ```

--- a/nvidia/trt-llm/README.md
+++ b/nvidia/trt-llm/README.md
@ -57,7 +57,7 @@ inference through kernel-level optimizations, efficient memory layouts, and adva

 - DGX Spark device
 - NVIDIA drivers compatible with CUDA 12.x: `nvidia-smi`
- Docker installed and GPU support configured: `docker run --rm --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc13 nvidia-smi`
+- Docker installed and GPU support configured: `docker run --rm --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 nvidia-smi`
 - Hugging Face account with token for model access: `echo $HF_TOKEN`
 - Sufficient GPU VRAM (40GB+ recommended for 70B models)
 - Internet connectivity for downloading models and container images
@ -75,9 +75,6 @@ The following models are supported with TensorRT-LLM on Spark. All listed models

 | Model | Quantization | Support Status | HF Handle |
 |-------|-------------|----------------|-----------|
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | BF16 | ✅ | `nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16` |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | FP8 | ✅ | `nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8` |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | NVFP4 | ✅ | `nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4` |
 | **Nemotron-3-Super-120B** | NVFP4 | ✅ | `nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4` |
 | **GPT-OSS-20B** | MXFP4 | ✅ | `openai/gpt-oss-20b` |
 | **GPT-OSS-120B** | MXFP4 | ✅ | `openai/gpt-oss-120b` |
@ -107,8 +104,8 @@ Reminder: not all model architectures are supported for NVFP4 quantization.
 * **Duration**: 45-60 minutes for setup and API server deployment
 * **Risk level**: Medium - container pulls and model downloads may fail due to network issues
 * **Rollback**: Stop inference servers and remove downloaded models to free resources.
-* **Last Updated:** 04/28/2026
-  * Docker image 1.3.0rc13; Nemotron Omni reasoning BF16, FP8, NVFP4 in matrix
+* **Last Updated:** 03/12/2026
+  * Introduce Nemotron-3-Super-120B support on TRT-LLM

 ## Single Spark

@ -139,7 +136,7 @@ models and containers.
 nvidia-smi

 ## Verify Docker GPU support
-docker run --rm --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc13 nvidia-smi
+docker run --rm --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6 nvidia-smi

 ```

@ -149,7 +146,7 @@ docker run --rm --gpus all nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc13 nvidia-
 ## Set `HF_TOKEN` for model access.
 export HF_TOKEN=<your-huggingface-token>

-export DOCKER_IMAGE="nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc13"
+export DOCKER_IMAGE="nvcr.io/nvidia/tensorrt-llm/release:1.2.0rc6"
 ```

 ## Step 4. Validate TensorRT-LLM installation
@ -164,8 +161,8 @@ docker run --rm -it --gpus all \

 Expected output:
 ```
-[TensorRT-LLM] TensorRT-LLM version: 1.3.0rc13
-TensorRT-LLM version: 1.3.0rc13
+[TensorRT-LLM] TensorRT-LLM version: 1.2.0rc6
+TensorRT-LLM version: 1.2.0rc6
 ```

 ## Step 5. Create cache directory
@ -293,43 +290,6 @@ sudo sh -c 'sync; echo 3 > /proc/sys/vm/drop_caches'

 Serve with OpenAI-compatible API via trtllm-serve:

-#### Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
-
-This example writes **`nano_v3.yaml`** for KV cache, MoE, and CUDA graph settings, then starts **`trtllm-serve`** on port **8000** with Nemotron Omni reasoning parsers.
-
-```bash
-export MODEL_HANDLE="nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16"
-
-docker run --name trtllm_llm_server --rm -it --gpus all --ipc host --network host \
-  -e HF_TOKEN=$HF_TOKEN \
-  -e MODEL_HANDLE="$MODEL_HANDLE" \
-  -v $HOME/.cache/huggingface/:/root/.cache/huggingface/ \
-  $DOCKER_IMAGE \
-  bash -c '
-    hf download $MODEL_HANDLE && \
-    cat > nano_v3.yaml <<EOF
-kv_cache_config:
-  enable_block_reuse: false
-  free_gpu_memory_fraction: 0.80
-  mamba_ssm_cache_dtype: float32
-moe_config:
-  backend: CUTLASS
-cuda_graph_config:
-  enable_padding: true
-  max_batch_size: 1
-max_batch_size: 1
-EOF
-    PYTORCH_ALLOC_CONF=expandable_segments:True \
-    trtllm-serve serve "$MODEL_HANDLE" \
-      --host 0.0.0.0 \
-      --port 8355 \
-      --trust_remote_code \
-      --reasoning_parser nano-v3 \
-      --tool_parser qwen3_coder \
-      --extra_llm_api_options nano_v3.yaml
-  '
-```
-
 #### Llama 3.1 8B Instruct
 ```bash
 export MODEL_HANDLE="nvidia/Llama-3.1-8B-Instruct-FP4"
@ -725,7 +685,6 @@ docker rmi ghcr.io/open-webui/open-webui:main
 | "invalid mount config for type 'bind'" | Missing or non-executable entrypoint script | Run `docker inspect <container_id>` to see full error message. Verify `trtllm-mn-entrypoint.sh` exists on both nodes in your home directory (`ls -la $HOME/trtllm-mn-entrypoint.sh`) and has executable permissions (`chmod +x $HOME/trtllm-mn-entrypoint.sh`) |
 | "task: non-zero exit (255)" | Container exit with error code 255 | Check container logs with `docker ps -a --filter "name=trtllm-multinode_trtllm"` to get container ID, then `docker logs <container_id>` to see detailed error messages |
 | Docker state stuck in "Pending" with "no suitable node (insufficien...)" | Docker daemon not properly configured for GPU access | Verify steps 2-4 were completed successfully and check that `/etc/docker/daemon.json` contains correct GPU configuration |
-| Serving model fails `ptxas fatal` errors | Model needs runtime triton kernel compilation | In Step 10, add `-x TRITON_PTXAS_PATH` to your `mpirun` command |

 > [!NOTE]
 > DGX Spark uses a Unified Memory Architecture (UMA), which enables dynamic memory sharing between the GPU and CPU.
--- a/nvidia/vllm/README.md
+++ b/nvidia/vllm/README.md
@ -54,9 +54,6 @@ The following models are supported with vLLM on Spark. All listed models are ava

 | Model | Quantization | Support Status | HF Handle |
 |-------|-------------|----------------|-----------|
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | BF16 | ✅ | [`nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16`](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16) |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | FP8 | ✅ | [`nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8`](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8) |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | NVFP4 | ✅ | [`nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4`](https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4) |
 | **Gemma 4 31B IT** | Base | ✅ | [`google/gemma-4-31B-it`](https://huggingface.co/google/gemma-4-31B-it) |
 | **Gemma 4 31B IT** | NVFP4 | ✅ | [`nvidia/Gemma-4-31B-IT-NVFP4`](https://huggingface.co/nvidia/Gemma-4-31B-IT-NVFP4) |
 | **Gemma 4 26B A4B IT** | Base | ✅ | [`google/gemma-4-26B-A4B-it`](https://huggingface.co/google/gemma-4-26B-A4B-it) |
@ -97,22 +94,12 @@ Reminder: not all model architectures are supported for NVFP4 quantization.
 * **Duration:** 30 minutes for Docker approach
 * **Risks:** Container registry access requires internal credentials
 * **Rollback:** Container approach is non-destructive.
-* **Last Updated:** 04/28/2026
-  * Add support for Nemotron-3-Nano-Omni reasoning BF16, FP8, NVFP4
+* **Last Updated:** 04/02/2026
+  * Add support for Gemma 4 model family

 ## Instructions

-## Step 1. Use model specific deployment guide
-
-Certain models require special deployment configurations. Please refer to their respective model cards to run on DGX Spark:
-
-| Model | Quantization | HF Model Card Link |
-|-------|-------------|----------------|
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | BF16 | https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | FP8 | https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8 |
-| **Nemotron-3-Nano-Omni-30B-A3B-Reasoning** | NVFP4 | https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 |
-
-## Step 2. Configure Docker permissions
+## Step 1. Configure Docker permissions

 To easily manage containers without sudo, you must be in the `docker` group. If you choose to skip this step, you will need to run Docker commands with sudo.

@ -128,7 +115,7 @@ sudo usermod -aG docker $USER
 newgrp docker
 ```

-## Step 3. Pull vLLM container image
+## Step 2. Pull vLLM container image

 Find the latest container build from https://catalog.ngc.nvidia.com/orgs/nvidia/containers/vllm

@ -149,7 +136,7 @@ For Gemma 4 model family, use vLLM custom containers:
 docker pull vllm/vllm-openai:gemma4-cu130
 ```

-## Step 4. Test vLLM in container
+## Step 3. Test vLLM in container

 Launch the container and start vLLM server with a test model to verify basic functionality.

@ -184,7 +171,7 @@ curl http://localhost:8000/v1/chat/completions \

 Expected response should contain `"content": "204"` or similar mathematical calculation.

-## Step 5. Cleanup and rollback
+## Step 4. Cleanup and rollback

 For container approach (non-destructive):

@ -193,7 +180,7 @@ docker rm $(docker ps -aq --filter ancestor=nvcr.io/nvidia/vllm:${LATEST_VLLM_VE
 docker rmi nvcr.io/nvidia/vllm
 ```

-## Step 6. Next steps
+## Step 5. Next steps

 - **Production deployment:** Configure vLLM with your specific model requirements
 - **Performance tuning:** Adjust batch sizes and memory settings for your workload