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, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("facebook/KernelLLM")
model = AutoModelForCausalLM.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

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
```

Zacharias030 commited on May 14, 2025

Commit

19545c6

verified ·

1 Parent(s): f5663dc

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -33,9 +33,9 @@ We finetuned Llama3.1-8B-Instruct on the created dataset using supervised instru
 | Model | Parameters (B) | Score | Pass@k |
 |-------|---------------|-------|--------|
-| KernelLLM | 8 | 15.5 | 1 |
-| KernelLLM | 8 | 34.7 | 10 |
-| KernelLLM | 8 | 39.8 | 20 |
 | DeepSeek V3 | 671 | 16 | 1 |
 | GPT-4o | ~200 | 15 | 1 |
 | Qwen2.5 | 32 | 15 | 1 |
@@ -127,7 +127,7 @@ model = KernelLLM()
 model.stream_raw("Your prompt here", max_new_tokens=2048)
 # Generate raw text without the Triton-specific prompt template
-raw_output = model.generate_raw("Your prompt here", temperature=0.6, max_new_tokens=2048)
 ```
 ## Current Limitations and Future Work

 | Model | Parameters (B) | Score | Pass@k |
 |-------|---------------|-------|--------|
+| KernelLLM | 8 | 20.2 | 1 |
+| KernelLLM | 8 | 51.8 | 10 |
+| KernelLLM | 8 | 57.1 | 20 |
 | DeepSeek V3 | 671 | 16 | 1 |
 | GPT-4o | ~200 | 15 | 1 |
 | Qwen2.5 | 32 | 15 | 1 |
 model.stream_raw("Your prompt here", max_new_tokens=2048)
 # Generate raw text without the Triton-specific prompt template
+raw_output = model.generate_raw("Your prompt here", temperature=1.0, max_new_tokens=2048)
 ```
 ## Current Limitations and Future Work