Instructions to use RedHatAI/Inkling-FP8-block with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Inkling-FP8-block with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/Inkling-FP8-block")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RedHatAI/Inkling-FP8-block")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/Inkling-FP8-block", 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?"}
        ]
    },
]
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/Inkling-FP8-block with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Inkling-FP8-block"
# 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/Inkling-FP8-block",
		"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/Inkling-FP8-block

SGLang

How to use RedHatAI/Inkling-FP8-block 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/Inkling-FP8-block" \
    --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/Inkling-FP8-block",
		"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/Inkling-FP8-block" \
        --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/Inkling-FP8-block",
		"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/Inkling-FP8-block with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Inkling-FP8-block
```

krishnateja95 commited on 27 days ago

Commit

5758b8d

verified ·

1 Parent(s): acee911

Remove outdated PR #48768 note, keep PR #48876 note

Browse files

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -39,9 +39,7 @@ Weights are quantized statically using 128x128 block-wise FP8 scaling, and activ
 This model can be deployed using [vLLM](https://docs.vllm.ai/en/latest/).
-> **Note:** Inkling model support in vLLM is being added in [vllm-project/vllm#48768](https://github.com/vllm-project/vllm/pull/48768). This PR is currently a draft and has not yet been merged, so you will need to install vLLM from that pull request's branch (`tml-inkling`) to run this model until it lands on `main`.
->
-> Additionally, FP8 quantization support for Inkling requires [vllm-project/vllm#48876](https://github.com/vllm-project/vllm/pull/48876).
 1. Start the vLLM server:
 ```

 This model can be deployed using [vLLM](https://docs.vllm.ai/en/latest/).
+> **Note:** FP8 quantization support for Inkling requires [vllm-project/vllm#48876](https://github.com/vllm-project/vllm/pull/48876).
 1. Start the vLLM server:
 ```