Instructions to use AscendKernelGen/KernelGen-LM-32B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AscendKernelGen/KernelGen-LM-32B-RL with Transformers:

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

pipe = pipeline("text-generation", model="AscendKernelGen/KernelGen-LM-32B-RL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AscendKernelGen/KernelGen-LM-32B-RL")
model = AutoModelForCausalLM.from_pretrained("AscendKernelGen/KernelGen-LM-32B-RL")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AscendKernelGen/KernelGen-LM-32B-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AscendKernelGen/KernelGen-LM-32B-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AscendKernelGen/KernelGen-LM-32B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AscendKernelGen/KernelGen-LM-32B-RL

SGLang

How to use AscendKernelGen/KernelGen-LM-32B-RL 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 "AscendKernelGen/KernelGen-LM-32B-RL" \
    --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": "AscendKernelGen/KernelGen-LM-32B-RL",
		"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 "AscendKernelGen/KernelGen-LM-32B-RL" \
        --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": "AscendKernelGen/KernelGen-LM-32B-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AscendKernelGen/KernelGen-LM-32B-RL with Docker Model Runner:
```
docker model run hf.co/AscendKernelGen/KernelGen-LM-32B-RL
```

KernelGen-LM-32B-RL

Commit History

Update README.md

8313603
verified

AscendKernelGen commited on 11 days ago

Upload 2 files

ca3e612
verified

AscendKernelGen commited on 11 days ago

Update README.md

46439bd
verified

AscendKernelGen commited on 12 days ago

Update README.md

96cb9aa
verified

AscendKernelGen commited on 12 days ago

Update README.md

70b452f
verified

AscendKernelGen commited on 15 days ago

Update README.md

83580bb
verified

AscendKernelGen commited on 15 days ago

Update README.md

e5493cc
verified

AscendKernelGen commited on 16 days ago

Add metadata and improve model card (#1)

27989ee

AscendKernelGen

nielsr HF Staff commited on 18 days ago

Update README.md

90c578f
verified

AscendKernelGen commited on Mar 13

Update README.md

b2aa9f6
verified

AscendKernelGen commited on Mar 13

Update README.md

101c1f4
verified

AscendKernelGen commited on Mar 13

Update README.md

d2f9f50
verified

AscendKernelGen commited on Jan 26

Update README.md

ff3f8ad
verified

AscendKernelGen commited on Jan 26

Update README.md

36404ef
verified

AscendKernelGen commited on Jan 26

Update README.md

4805bd0
verified

AscendKernelGen commited on Jan 26

Update README.md

2e4e618
verified

AscendKernelGen commited on Jan 26

Update README.md

e087df2
verified

AscendKernelGen commited on Jan 26

Update README.md

9d5531e
verified

AscendKernelGen commited on Jan 26

Update README.md

5ce667d
verified

AscendKernelGen commited on Jan 26

Update README.md

054c08a
verified

AscendKernelGen commited on Jan 26

Update README.md

92fae39
verified

AscendKernelGen commited on Jan 26

Update README.md

6c43949
verified

AscendKernelGen commited on Jan 26

Update README.md

796bca4
verified

AscendKernelGen commited on Jan 26

Create README.md

754670c
verified

AscendKernelGen commited on Jan 26

Upload folder using huggingface_hub

8a92d19
verified

AscendKernelGen commited on Jan 25

initial commit

ad5a1b6
verified

AscendKernelGen commited on Jan 23

Commit History

Update README.md 8313603 verified

Upload 2 files ca3e612 verified

Update README.md 46439bd verified

Update README.md 96cb9aa verified

Update README.md 70b452f verified

Update README.md 83580bb verified

Update README.md e5493cc verified

Add metadata and improve model card (#1) 27989ee

Update README.md 90c578f verified

Update README.md b2aa9f6 verified

Update README.md 101c1f4 verified

Update README.md d2f9f50 verified

Update README.md ff3f8ad verified

Update README.md 36404ef verified

Update README.md 4805bd0 verified

Update README.md 2e4e618 verified

Update README.md e087df2 verified

Update README.md 9d5531e verified

Update README.md 5ce667d verified

Update README.md 054c08a verified

Update README.md 92fae39 verified

Update README.md 6c43949 verified

Update README.md 796bca4 verified

Create README.md 754670c verified

Upload folder using huggingface_hub 8a92d19 verified

initial commit ad5a1b6 verified

Update README.md

8313603
verified

Upload 2 files

ca3e612
verified

Update README.md

46439bd
verified

Update README.md

96cb9aa
verified

Update README.md

70b452f
verified

Update README.md

83580bb
verified

Update README.md

e5493cc
verified

Add metadata and improve model card (#1)

27989ee

Update README.md

90c578f
verified

Update README.md

b2aa9f6
verified

Update README.md

101c1f4
verified

Update README.md

d2f9f50
verified

Update README.md

ff3f8ad
verified

Update README.md

36404ef
verified

Update README.md

4805bd0
verified

Update README.md

2e4e618
verified

Update README.md

e087df2
verified

Update README.md

9d5531e
verified

Update README.md

5ce667d
verified

Update README.md

054c08a
verified

Update README.md

92fae39
verified

Update README.md

6c43949
verified

Update README.md

796bca4
verified

Create README.md

754670c
verified

Upload folder using huggingface_hub

8a92d19
verified

initial commit

ad5a1b6
verified