Instructions to use moonshotai/Kimi-VL-A3B-Thinking-2506 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-VL-A3B-Thinking-2506 with Transformers:

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

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-VL-A3B-Thinking-2506", 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("moonshotai/Kimi-VL-A3B-Thinking-2506", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-VL-A3B-Thinking-2506 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-VL-A3B-Thinking-2506"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-VL-A3B-Thinking-2506",
		"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/moonshotai/Kimi-VL-A3B-Thinking-2506

SGLang

How to use moonshotai/Kimi-VL-A3B-Thinking-2506 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 "moonshotai/Kimi-VL-A3B-Thinking-2506" \
    --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": "moonshotai/Kimi-VL-A3B-Thinking-2506",
		"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 "moonshotai/Kimi-VL-A3B-Thinking-2506" \
        --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": "moonshotai/Kimi-VL-A3B-Thinking-2506",
		"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 moonshotai/Kimi-VL-A3B-Thinking-2506 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-VL-A3B-Thinking-2506
```

zhouzaida commited on Aug 18, 2025

Commit

5b60bb1

verified ·

1 Parent(s): 04caee9

remove _validate_images_text_input_order as well (#11)

Browse files

- remove _validate_images_text_input_order (6bd580e019050d4ca04dc317a70df881628c1cb6)

Files changed (1) hide show

processing_kimi_vl.py +1 -3

processing_kimi_vl.py CHANGED Viewed

@@ -22,7 +22,7 @@ from typing import List, Union
 from transformers.feature_extraction_utils import BatchFeature
 from transformers.image_utils import ImageInput
-from transformers.processing_utils import ProcessingKwargs, ProcessorMixin, Unpack, _validate_images_text_input_order
 from transformers.tokenization_utils_base import PreTokenizedInput, TextInput
 from transformers.utils import logging
@@ -110,8 +110,6 @@ class KimiVLProcessor(ProcessorMixin):
         if images is None and text is None:
             raise ValueError("You have to specify at least one of `images` or `text`.")
-        # check if images and text inputs are reversed for BC
-        images, text = _validate_images_text_input_order(images, text)
         output_kwargs = self._merge_kwargs(
             KimiVLProcessorKwargs,

 from transformers.feature_extraction_utils import BatchFeature
 from transformers.image_utils import ImageInput
+from transformers.processing_utils import ProcessingKwargs, ProcessorMixin, Unpack
 from transformers.tokenization_utils_base import PreTokenizedInput, TextInput
 from transformers.utils import logging
         if images is None and text is None:
             raise ValueError("You have to specify at least one of `images` or `text`.")
         output_kwargs = self._merge_kwargs(
             KimiVLProcessorKwargs,