Instructions to use RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16")
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-VL-72B-Instruct-quantized.w4a16")
model = AutoModelForImageTextToText.from_pretrained("RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16")
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

vLLM

How to use RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16"
# 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-VL-72B-Instruct-quantized.w4a16",
		"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-VL-72B-Instruct-quantized.w4a16

SGLang

How to use RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16 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-VL-72B-Instruct-quantized.w4a16" \
    --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-VL-72B-Instruct-quantized.w4a16",
		"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-VL-72B-Instruct-quantized.w4a16" \
        --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-VL-72B-Instruct-quantized.w4a16",
		"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-VL-72B-Instruct-quantized.w4a16 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16
```

shubhrapandit commited on Mar 3, 2025

Commit

0d2af68

verified ·

1 Parent(s): bbbee32

Update README.md

Browse files

Files changed (1) hide show

README.md +25 -25

README.md CHANGED Viewed

@@ -307,7 +307,7 @@ lm_eval \
 ## Inference Performance
-This model achieves up to xxx speedup in single-stream deployment and up to xxx speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 <details>
@@ -459,22 +459,22 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w8a8</td>
       <td>1.84</td>
-      <td>1.2</td>
-      <td>586</td>
-      <td>4.0</td>
-      <td>2042</td>
-      <td>4.6</td>
-      <td>2270</td>
     </tr>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16</td>
       <td>2.73</td>
-      <td>2.4</td>
-      <td>1256</td>
-      <td>12.8</td>
-      <td>6364</td>
-      <td>16.0</td>
-      <td>8076</td>
     </tr>
     <tr>
       <th rowspan="3" valign="top">H100x4</td>
@@ -490,22 +490,22 @@ The following performance benchmarks were conducted with [vLLM](https://docs.vll
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic</td>
       <td>1.70</td>
-      <td>1.6</td>
-      <td>457</td>
-      <td>4.4</td>
-      <td>1207</td>
-      <td>4.8</td>
-      <td>1296</td>
     </tr>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16</td>
       <td>2.35</td>
-      <td>5.2</td>
-      <td>1400</td>
-      <td>13.2</td>
-      <td>3640</td>
-      <td>14.4</td>
-      <td>3976</td>
     </tr>
   </tbody>
 </table>

 ## Inference Performance
+This model achieves up to 3.7x speedup in single-stream deployment and up to 3.3x speedup in multi-stream asynchronous deployment, depending on hardware and use-case scenario.
 The following performance benchmarks were conducted with [vLLM](https://docs.vllm.ai/en/latest/) version 0.7.2, and [GuideLLM](https://github.com/neuralmagic/guidellm).
 <details>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w8a8</td>
       <td>1.84</td>
+      <td>0.6</td>
+      <td>293</td>
+      <td>2.0</td>
+      <td>1021</td>
+      <td>2.3</td>
+      <td>1135</td>
     </tr>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16</td>
       <td>2.73</td>
+      <td>0.6</td>
+      <td>314</td>
+      <td>3.2</td>
+      <td>1591</td>
+      <td>4.0</td>
+      <td>2019</td>
     </tr>
     <tr>
       <th rowspan="3" valign="top">H100x4</td>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-FP8-Dynamic</td>
       <td>1.70</td>
+      <td>0.8</td>
+      <td>236</td>
+      <td>2.2</td>
+      <td>623</td>
+      <td>2.4</td>
+      <td>669</td>
     </tr>
     <tr>
       <td>neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16</td>
       <td>2.35</td>
+      <td>1.3</td>
+      <td>350</td>
+      <td>3.3</td>
+      <td>910</td>
+      <td>3.6</td>
+      <td>994</td>
     </tr>
   </tbody>
 </table>