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

Libraries

How to use moonshotai/Kimi-VL-A3B-Instruct 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-Instruct", trust_remote_code=True, device_map="auto")
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-Instruct", trust_remote_code=True, dtype="auto", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-VL-A3B-Instruct 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-Instruct"
# 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-Instruct",
		"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-Instruct

SGLang

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

Fix the AttributeError: 'KimiVLForConditionalGeneration' object has no attribute '_supports_sdpa' issue after bumping to transformers==4.54.0

#29

by hebiao064 - opened Jul 29, 2025

base: refs/heads/main

←

from: refs/pr/29

Discussion Files changed

-8

Files changed (1) hide show

modeling_kimi_vl.py +1 -8

modeling_kimi_vl.py CHANGED Viewed

@@ -2406,6 +2406,7 @@ class KimiVLPreTrainedModel(PreTrainedModel, GenerationMixin):
     _no_split_modules = ["MoonVitEncoderLayer", "DeepseekV3DecoderLayer"]
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
     def _init_weights(self, module):
         # important: this ported version of Llava isn't meant for training from scratch - only
@@ -2429,14 +2430,6 @@ class KimiVLPreTrainedModel(PreTrainedModel, GenerationMixin):
             if module.padding_idx is not None:
                 module.weight.data[module.padding_idx].zero_()
-    @property
-    def _supports_sdpa(self):
-        """
-        Retrieve language_model's attribute to check whether the model supports
-        SDPA or not.
-        """
-        return self.language_model._supports_sdpa
 class KimiVLForConditionalGeneration(KimiVLPreTrainedModel, GenerationMixin):

     _no_split_modules = ["MoonVitEncoderLayer", "DeepseekV3DecoderLayer"]
     _skip_keys_device_placement = "past_key_values"
     _supports_flash_attn_2 = True
+    _supports_sdpa = False
     def _init_weights(self, module):
         # important: this ported version of Llava isn't meant for training from scratch - only
             if module.padding_idx is not None:
                 module.weight.data[module.padding_idx].zero_()
 class KimiVLForConditionalGeneration(KimiVLPreTrainedModel, GenerationMixin):