Instructions to use RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic")
model = AutoModelForImageTextToText.from_pretrained("RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic

SGLang

How to use RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic
```

shubhrapandit commited on Feb 26, 2025

Commit

7a1c418

verified ·

1 Parent(s): ac8d74d

Update README.md

Browse files

Files changed (1) hide show

README.md +63 -1

README.md CHANGED Viewed

@@ -277,6 +277,37 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     </tr>
   </thead>
   <tbody style="text-align: center">
     <tr>
       <th rowspan="3" valign="top">A100x1</th>
       <th>Qwen/Qwen2.5-VL-7B-Instruct</th>
@@ -371,9 +402,40 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     </tr>
   </thead>
   <tbody style="text-align: center">
      <tr>
       <th rowspan="3" valign="top">A100x1</th>
-      <th>Qwen/Qwen2.5-VL-7B-Instruct-quantized.</th>
       <td></td>
       <td>0.7</td>
       <td>1347</td>

     </tr>
   </thead>
   <tbody style="text-align: center">
+       <tr>
+      <th rowspan="3" valign="top">A6000x1</th>
+      <th>Qwen/Qwen2.5-VL-7B-Instruct</th>
+      <td></td>
+      <td>4.9</td>
+      <td>912</td>
+      <td>3.2</td>
+      <td>1386</td>
+      <td>3.1</td>
+      <td>1431</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/Qwen2.5-VL-7B-Instruct-quantized.w8a8</th>
+      <td>1.50</td>
+      <td>3.6</td>
+      <td>1248</td>
+      <td>2.1</td>
+      <td>2163</td>
+      <td>2.0</td>
+      <td>2237</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/Qwen2.5-VL-7B-Instruct-quantized.w4a16</th>
+      <td>2.05</td>
+      <td>3.3</td>
+      <td>1351</td>
+      <td>1.4</td>
+      <td>3252</td>
+      <td>1.4</td>
+      <td>3321</td>
+    </tr>
     <tr>
       <th rowspan="3" valign="top">A100x1</th>
       <th>Qwen/Qwen2.5-VL-7B-Instruct</th>
     </tr>
   </thead>
   <tbody style="text-align: center">
+    <tr>
+      <th rowspan="3" valign="top">A6000x1</th>
+      <th>Qwen/Qwen2.5-VL-7B-Instruct</th>
+      <td></td>
+      <td>0.4</td>
+      <td>1837</td>
+      <td>1.5</td>
+      <td>6846</td>
+      <td>1.7</td>
+      <td>7638</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/Qwen2.5-VL-7B-Instruct-quantized.w8a8</th>
+      <td>1.41</td>
+      <td>0.5</td>
+      <td>2297</td>
+      <td>2.3</td>
+      <td>10137</td>
+      <td>2.5</td>
+      <td>11472</td>
+    </tr>
+    <tr>
+      <th>neuralmagic/Qwen2.5-VL-7B-Instruct-quantized.w4a16</th>
+      <td>1.60</td>
+      <td>0.4</td>
+      <td>1828</td>
+      <td>2.7</td>
+      <td>12254</td>
+      <td>3.4</td>
+      <td>15477</td>
+    </tr>
      <tr>
       <th rowspan="3" valign="top">A100x1</th>
+      <th>Qwen/Qwen2.5-VL-7B-Instruct</th>
       <td></td>
       <td>0.7</td>
       <td>1347</td>