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

Libraries

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

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

pipe = pipeline("text-generation", model="AscendKernelGen/KernelGen-LM-32B")
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")
model = AutoModelForCausalLM.from_pretrained("AscendKernelGen/KernelGen-LM-32B")
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 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

AscendKernelGen commited on Mar 13

Commit

20d682c

verified ·

1 Parent(s): 2a6428e

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -7,14 +7,14 @@ language:
 # AscendKernelGen/KernelGen-LM-32B
 ![License](https://img.shields.io/badge/License-Apache-yellow)
-[![arXiv](https://img.shields.io/badge/arXiv-2601.07160-b31b1b.svg)](https://arxiv.org/abs/2601.07160)
 KernelGen-LM-32B is a state-of-the-art domain-adaptive large language model specialized for low-level NPU kernel generation, specifically for the Huawei Ascend architecture using the AscendC programming language. Built upon the Qwen3-32B backbone, it is trained on the Ascend-CoT dataset and refined via reinforcement learning with execution feedback. It achieves unprecedented success rates in generating complex, functional hardware kernels, improving compilation success on L2 tasks from 0% (baseline) to 96.5% (Pass@10), while functional correctness achieves
 40.5% compared to the baseline’s complete failure.
-**Other artifacts:**
 * The **AscendKernelGen Technical Report** is published at https://arxiv.org/abs/2601.07160.
-* The **NPUKernelBench** evaluation framework is published at https://git.openi.org.cn/PCL-Benchmark/NPUKernelBench.
 ## Introduction

 # AscendKernelGen/KernelGen-LM-32B
 ![License](https://img.shields.io/badge/License-Apache-yellow)
+<!-- [![arXiv](https://img.shields.io/badge/arXiv-2601.07160-b31b1b.svg)](https://arxiv.org/abs/2601.07160) -->
 KernelGen-LM-32B is a state-of-the-art domain-adaptive large language model specialized for low-level NPU kernel generation, specifically for the Huawei Ascend architecture using the AscendC programming language. Built upon the Qwen3-32B backbone, it is trained on the Ascend-CoT dataset and refined via reinforcement learning with execution feedback. It achieves unprecedented success rates in generating complex, functional hardware kernels, improving compilation success on L2 tasks from 0% (baseline) to 96.5% (Pass@10), while functional correctness achieves
 40.5% compared to the baseline’s complete failure.
+<!-- **Other artifacts:**
 * The **AscendKernelGen Technical Report** is published at https://arxiv.org/abs/2601.07160.
+* The **NPUKernelBench** evaluation framework is published at https://git.openi.org.cn/PCL-Benchmark/NPUKernelBench. -->
 ## Introduction