Merge pull request #255 from tokk-nv/dev/nvme-message

Change storage requirement message
NVIDIA-AI-IOT · Jan 22, 2025 · c27aa46 · c27aa46
2 parents 658c687 + 51e315a
commit c27aa46
Show file tree

Hide file tree

Showing 34 changed files with 39 additions and 34 deletions.
diff --git a/docs/agent_studio.md b/docs/agent_studio.md
@@ -44,7 +44,7 @@ Rapidly design and experiment with creating your own automation agents, personal
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models (`>5GB`)

diff --git a/docs/cosmos.md b/docs/cosmos.md
@@ -24,7 +24,7 @@ inference scripts and generate videos.
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `12.26GB` for [`cosmos`](https://hub.docker.com/r/dustynv/cosmos) container image
         - Space for models and datasets (`>50GB`)

diff --git a/docs/css/colors.css b/docs/css/colors.css
@@ -246,6 +246,11 @@ a.nv-buy-link:hover,.load-buy-link:hover {
 	background: #222; color: #FFF; font-size: 0.8em; border-radius: 0.3em;  padding-left: 0.3em; padding-right: 0.3em;  margin: 0.2em; 
 }
 
+.markedYellow {
+	background: #dfff00;
+	padding: 0.2em
+}
+
 .highlightYellow {
 	background: #ffc105;
     border-radius: 0.5em;  

diff --git a/docs/lerobot.md b/docs/lerobot.md
@@ -17,7 +17,7 @@ Let's run HuggingFace [`LeRobot`](https://github.com/huggingface/lerobot/) to tr
 
         <span class="blobPink2">JetPack 6 GA (L4T r36.3)</span> <span class="blobPink1">JetPack 6.1 (L4T r36.4)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `16.5GB` for [`lerobot`](https://hub.docker.com/r/dustynv/lerobot) container image
         - Space for models (`>2GB`)

diff --git a/docs/llama_vlm.md b/docs/llama_vlm.md
@@ -20,7 +20,7 @@ While quantization and optimization efforts are underway, we have started with r
 
         <span class="blobPink2">JetPack 6 (L4T r36)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `12.8GB` for `llama-vision` container image
         - Space for models (`>25GB`)

diff --git a/docs/nerf.md b/docs/nerf.md
@@ -19,7 +19,7 @@
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `17.6GB` for [`nerfstudio`](https://hub.docker.com/r/dustynv/nerfstudio) container image
         - Space for models and datasets (`>5GB`)

diff --git a/docs/openvla.md b/docs/openvla.md
@@ -45,7 +45,7 @@ OpenVLA reserves 256 of the least-frequently used tokens out of the Llama-7B voc
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models and datasets (`>15GB`)

diff --git a/docs/ros.md b/docs/ros.md
@@ -19,7 +19,7 @@ The [`ros2_nanollm`](https://github.com/NVIDIA-AI-IOT/ros2_nanollm) package prov
         <span class="blobPink2">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm:humble` container image
         - Space for models (`>10GB`)

diff --git a/docs/tensorrt_llm.md b/docs/tensorrt_llm.md
@@ -17,7 +17,7 @@ We've provided pre-compiled TensorRT-LLM [wheels](http://jetson.webredirect.org/
 
         <span class="blobPink2">JetPack 6.1 (L4T r36.4)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `18.5GB` for `tensorrt_llm` container image
         - Space for models (`>10GB`)

diff --git a/docs/tutorial_api-examples.md b/docs/tutorial_api-examples.md
@@ -16,7 +16,7 @@ It's good to know the code for generating text with LLM inference, and ancillary
         <span class="blobPink2">JetPack 5 (L4T r35)</span>
         <span class="blobPink2">JetPack 6 (L4T r36)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `l4t-text-generation` container image
         - Space for models (`>10GB`)

diff --git a/docs/tutorial_audiocraft.md b/docs/tutorial_audiocraft.md
@@ -14,7 +14,7 @@ Let's run Meta's [AudioCraft](https://github.com/facebookresearch/audiocraft), t
 
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `10.7 GB` for `audiocraft` container image
         - Space for checkpoints

diff --git a/docs/tutorial_holoscan.md b/docs/tutorial_holoscan.md
@@ -25,7 +25,7 @@ So, let's walk through how to run the Surgical Tool Tracking example application
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 	   
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `13.7 GB` for `efficientvit` container image
         - `850 Mb` for Tool Tracking ONNX model + example video

diff --git a/docs/tutorial_jetson-copilot.md b/docs/tutorial_jetson-copilot.md
@@ -20,7 +20,7 @@
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6 GB` for `jetrag` container image
         - About `4 GB` for downloading some default models (`llama3` and `mxbai-embed-large`)

diff --git a/docs/tutorial_jps.md b/docs/tutorial_jps.md
@@ -18,7 +18,7 @@ Jetson Plaform Services (JPS) provide a platform to simplify development, deploy
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 	   
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
 To get started with Jetson Platform Services, follow the quickstart guide to install and setup JPS. Then explore the reference workflows to learn how to use DeepStream, Analytics, Generative AI and more with JPS:
 

diff --git a/docs/tutorial_live-llava.md b/docs/tutorial_live-llava.md
@@ -27,7 +27,7 @@ It uses models like [LLaVA](https://llava-vl.github.io/){:target="_blank"} or [V
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models (`>10GB`)

diff --git a/docs/tutorial_llamaindex.md b/docs/tutorial_llamaindex.md
@@ -15,7 +15,7 @@ Let's use [LlamaIndex](https://www.llamaindex.ai/), to realize RAG (Retrieval Au
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `5.5 GB` for `llama-index` container image
         - Space for checkpoints

diff --git a/docs/tutorial_llamaspeak.md b/docs/tutorial_llamaspeak.md
@@ -23,7 +23,7 @@ The [`WebChat`](https://dusty-nv.github.io/NanoLLM/agents.html#web-chat){:target
 
         <span class="blobPink2">JetPack 6 (L4T r36)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models (`>10GB`)

diff --git a/docs/tutorial_llava.md b/docs/tutorial_llava.md
@@ -33,7 +33,7 @@ In addition to Llava, the [`NanoVLM`](tutorial_nano-vlm.md) pipeline supports [V
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.2GB` for `text-generation-webui` container image
         - Space for models
@@ -90,7 +90,7 @@ Go to **Chat** tab, drag and drop an image into the **Drop Image Here** area, an
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.1GB` for `llava` container
         - `14GB` for Llava-7B (or `26GB` for Llava-13B)

diff --git a/docs/tutorial_minigpt4.md b/docs/tutorial_minigpt4.md
@@ -17,7 +17,7 @@ Give your locally running LLM an access to vision, by running [MiniGPT-4](https:
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `5.8GB` for container image
         - Space for [pre-quantized MiniGPT-4 model](https://github.com/Maknee/minigpt4.cpp/tree/master#3-obtaining-the-model)

diff --git a/docs/tutorial_nano-vlm.md b/docs/tutorial_nano-vlm.md
@@ -27,7 +27,7 @@ This FPS measures the end-to-end pipeline performance for continuous streaming l
 
         <span class="blobPink2">JetPack 6 (L4T r36)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models (`>10GB`)

diff --git a/docs/tutorial_nanodb.md b/docs/tutorial_nanodb.md
@@ -18,7 +18,7 @@ Let's run [NanoDB](https://github.com/dusty-nv/jetson-containers/blob/master/pac
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `16GB` for container image
         - `40GB` for MS COCO dataset

diff --git a/docs/tutorial_ollama.md b/docs/tutorial_ollama.md
@@ -28,7 +28,7 @@ In this tutorial, we introduce two installation methods: (1) the default native
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `7GB` for `ollama` container image
         - Space for models (`>5GB`)

diff --git a/docs/tutorial_openwebui.md b/docs/tutorial_openwebui.md
@@ -22,7 +22,7 @@ It can work with Ollama as a backend as well as other backend that is compatible
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `7GB` for `open-webui` container image
 		 

diff --git a/docs/tutorial_slm.md b/docs/tutorial_slm.md
@@ -33,7 +33,7 @@ Based on user interactions, the recommended models to try are [`stabilityai/stab
 
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `22GB` for `nano_llm` container image
         - Space for models (`>5GB`)

diff --git a/docs/tutorial_stable-diffusion-xl.md b/docs/tutorial_stable-diffusion-xl.md
@@ -16,7 +16,7 @@
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.8GB` for container image
         - `12.4GB` for SDXL models

diff --git a/docs/tutorial_stable-diffusion.md b/docs/tutorial_stable-diffusion.md
@@ -18,7 +18,7 @@ Let's run AUTOMATIC1111's [`stable-diffusion-webui`](https://github.com/AUTOMATI
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.8GB` for container image
         - `4.1GB` for SD 1.5 model

diff --git a/docs/tutorial_text-generation.md b/docs/tutorial_text-generation.md
@@ -18,7 +18,7 @@ Interact with a local AI assistant by running a LLM with oobabooga's [`text-gene
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.2GB` for container image
         - Spaces for models

diff --git a/docs/tutorial_voicecraft.md b/docs/tutorial_voicecraft.md
@@ -14,7 +14,7 @@ Let's run [VoiceCraft](https://github.com/jasonppy/VoiceCraft), a Zero-Shot Spee
         <!-- <span class="blobPink1">JetPack 5 (L4T r35.x)</span> -->
          <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `15.6 GB` for `voicecraft` container image
         - Space for models

diff --git a/docs/tutorial_whisper.md b/docs/tutorial_whisper.md
@@ -16,7 +16,7 @@ Let's run OpenAI's [Whisper](https://github.com/openai/whisper), pre-trained mod
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.1 GB` for `whisper` container image
         - Space for checkpoints

diff --git a/docs/vit/tutorial_efficientvit.md b/docs/vit/tutorial_efficientvit.md
@@ -16,7 +16,7 @@ Let's run MIT Han Lab's [EfficientViT](https://github.com/mit-han-lab/efficientv
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 	   
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `10.9 GB` for `efficientvit` container image
         - Space for checkpoints

diff --git a/docs/vit/tutorial_nanoowl.md b/docs/vit/tutorial_nanoowl.md
@@ -18,7 +18,7 @@ Let's run [NanoOWL](https://github.com/NVIDIA-AI-IOT/nanoowl), [OWL-ViT](https:/
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `7.2 GB` for container image
         - Spaces for models

diff --git a/docs/vit/tutorial_nanosam.md b/docs/vit/tutorial_nanosam.md
@@ -18,7 +18,7 @@ Let's run NVIDIA's [NanoSAM](https://github.com/NVIDIA-AI-IOT/nanosam) to check
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.3GB` for container image
         - Spaces for models

diff --git a/docs/vit/tutorial_sam.md b/docs/vit/tutorial_sam.md
@@ -18,7 +18,7 @@ Let's run Meta's [`SAM`](https://github.com/facebookresearch/segment-anything) o
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
         <span class="blobPink2">JetPack 6 (L4T r36.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.8GB` for container image
         - Spaces for models

diff --git a/docs/vit/tutorial_tam.md b/docs/vit/tutorial_tam.md
@@ -15,7 +15,7 @@ Let's run [`TAM`](https://github.com/gaomingqi/Track-Anything) to perform Segmen
 
         <span class="blobPink1">JetPack 5 (L4T r35.x)</span>
 
-    3. Sufficient storage space (preferably with NVMe SSD).
+    3. <span class="markedYellow">NVMe SSD **highly recommended**</span> for storage speed and space
 
         - `6.8GB` for container image
         - Spaces for models