Instructions to use OpenGVLab/InternVL3_5-38B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3_5-38B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3_5-38B", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL3_5-38B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3_5-38B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3_5-38B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL3_5-38B",
		"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/OpenGVLab/InternVL3_5-38B

SGLang

How to use OpenGVLab/InternVL3_5-38B 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 "OpenGVLab/InternVL3_5-38B" \
    --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": "OpenGVLab/InternVL3_5-38B",
		"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 "OpenGVLab/InternVL3_5-38B" \
        --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": "OpenGVLab/InternVL3_5-38B",
		"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 OpenGVLab/InternVL3_5-38B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3_5-38B
```

vLLM compatiblility

by 4o4notf0und - opened Aug 28, 2025

Discussion

4o4notf0und

Aug 28, 2025

Hi team — thanks for the great work on InternVL3.5!

I noticed the checkpoints use processor_class: "InternVLProcessor", which expects extra special tokens (e.g., start_image_token). Those entries aren’t present in tokenizer_config.json, which prevents serving with vLLM. Is there a plan to make the releases vLLM-compatible (e.g., by including these tokens or publishing guidance/workarounds)?

Thanks!

4o4notf0und changed discussion status to closed Aug 28, 2025

4o4notf0und changed discussion status to open Aug 29, 2025

abiteddie

Sep 2, 2025

vllm tool calls not working

vllm serve '/mnt/models/vllm_models/InternVL3_5-38B-AWQ-8bit/' --max_model_len 32000 --tensor-parallel-size 8 --gpu_memory_utilization 0.95 --trust-remote-code --dtype float16 --enable-auto-tool-choice --tool-call-parser internlm

maroahma

Sep 2, 2025

is this issue resolved ? I'm also facing this

Weiyun1025

OpenGVLab org Sep 3, 2025

Can you provide the version of vLLM you used? I tested it with 0.8.5.post1 and 0.10.1 and found that it works well.

maroahma

Sep 3, 2025

•

edited Sep 3, 2025

Version: 0.10.1rc2.dev294+gc9c3a7856.cu124

Also is the HF version for 3.5 not supported on VLLM for llm. generate ? THe same is happening for internVL 3 38B hf in the same vllm version

I can share the logs if you want

maroahma

Sep 3, 2025

Also is the HF version for 3.5 not supported on VLLM for llm. generate ? THe same is happening for internVL 3 38B hf in the same vllm version

4o4notf0und

Sep 3, 2025

•

edited Sep 3, 2025

Can you provide the version of vLLM you used? I tested it with 0.8.5.post1 and 0.10.1 and found that it works well.

When I tried to serve the model, it did work because VLLM holds multiple strategies to get the chat template here. However, cached_get_processor always raises errors due to the missing special tokens, which breaks the cache and therefore, executes AutoProcessor.from_pretrained(...) for every request. The service will then be down due to HTTP Error 429 caused by repetitive HEAD operations to HuggingFace.

4o4notf0und changed discussion status to closed Sep 3, 2025

4o4notf0und changed discussion status to open Sep 3, 2025

vcerny

Sep 27, 2025

•

edited Sep 27, 2025

Any fresh experience with making tool calling work with vLLM? Thanks!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment