Instructions to use facebook/KernelLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use facebook/KernelLLM with Transformers:

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

pipe = pipeline("text-generation", model="facebook/KernelLLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("facebook/KernelLLM")
model = AutoModelForMultimodalLM.from_pretrained("facebook/KernelLLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use facebook/KernelLLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "facebook/KernelLLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "facebook/KernelLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/facebook/KernelLLM

SGLang

How to use facebook/KernelLLM 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 "facebook/KernelLLM" \
    --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": "facebook/KernelLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "facebook/KernelLLM" \
        --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": "facebook/KernelLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use facebook/KernelLLM with Docker Model Runner:
```
docker model run hf.co/facebook/KernelLLM
```

add citation

by marksaroufim - opened May 26, 2025

base: refs/heads/main

←

from: refs/pr/6

Discussion Files changed

+11

-0

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -177,6 +177,17 @@ KernelLLM and its variants are a new technology that carries risks with use. Tes
 Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide).
 ## Acknowledgements
 KernelLLM would not be possible if it was not for our close collaboration with [Simon Guo](https://simonguo.tech/) and [Simran Arora](https://arorasimran.com/) from Stanford and [Alex Zhang](https://alexzhang13.github.io/). To learn more about how KernelLLM was a community project, you can watch our talks at [GPU MODE @ GTC](https://www.youtube.com/watch?v=FtgXueoQkA0)

 Please see the Responsible Use Guide available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide).
+## Citation
+@misc{kernelllm2025,
+    title={KernelLLM},
+    author={Fisches, Zacharias and Paliskara, Sahan and Guo, Simon and Zhang, Alex and Spisak, Joe and Cummins, Chris and Leather, Hugh and Isaacson, Joe and Markosyan, Aram and Saroufim, Mark},
+    year={2025},
+    month={5},
+    note={Corresponding authors: Aram Markosyan, Mark Saroufim},
+    url={https://huggingface.co/facebook/KernelLLM},
+}
 ## Acknowledgements
 KernelLLM would not be possible if it was not for our close collaboration with [Simon Guo](https://simonguo.tech/) and [Simran Arora](https://arorasimran.com/) from Stanford and [Alex Zhang](https://alexzhang13.github.io/). To learn more about how KernelLLM was a community project, you can watch our talks at [GPU MODE @ GTC](https://www.youtube.com/watch?v=FtgXueoQkA0)