Instructions to use AscendKernelGen/KernelGen-LM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AscendKernelGen/KernelGen-LM-8B with Transformers:

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

pipe = pipeline("text-generation", model="AscendKernelGen/KernelGen-LM-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AscendKernelGen/KernelGen-LM-8B")
model = AutoModelForCausalLM.from_pretrained("AscendKernelGen/KernelGen-LM-8B")
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-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AscendKernelGen/KernelGen-LM-8B"
# 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-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AscendKernelGen/KernelGen-LM-8B

SGLang

How to use AscendKernelGen/KernelGen-LM-8B 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-8B" \
    --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-8B",
		"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-8B" \
        --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-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AscendKernelGen/KernelGen-LM-8B with Docker Model Runner:
```
docker model run hf.co/AscendKernelGen/KernelGen-LM-8B
```

KernelGen-LM-8B

Commit History

Update README.md

b2491b2
verified

AscendKernelGen commited on 10 days ago

Upload 2 files

6bc2515
verified

AscendKernelGen commited on 10 days ago

Update README.md

ede6d36
verified

AscendKernelGen commited on 11 days ago

Update README.md

39b96eb
verified

AscendKernelGen commited on 11 days ago

Update README.md

11d7026
verified

AscendKernelGen commited on 14 days ago

Update README.md

7588ed0
verified

AscendKernelGen commited on 15 days ago

Add model metadata and links to paper and code (#1)

c3ff880

AscendKernelGen

nielsr HF Staff commited on 17 days ago

Update README.md

8e74169
verified

AscendKernelGen commited on Mar 13

Update README.md

6ed17a3
verified

AscendKernelGen commited on Mar 13

Update README.md

ae3a39f
verified

AscendKernelGen commited on Mar 13

Update README.md

c79ed3c
verified

AscendKernelGen commited on Jan 26

Create README.md

3fec8ed
verified

AscendKernelGen commited on Jan 26

Upload folder using huggingface_hub

4b88149
verified

AscendKernelGen commited on Jan 24

initial commit

6c104e4
verified

AscendKernelGen commited on Jan 23

Commit History

Update README.md b2491b2 verified

Upload 2 files 6bc2515 verified

Update README.md ede6d36 verified

Update README.md 39b96eb verified

Update README.md 11d7026 verified

Update README.md 7588ed0 verified

Add model metadata and links to paper and code (#1) c3ff880

Update README.md 8e74169 verified

Update README.md 6ed17a3 verified

Update README.md ae3a39f verified

Update README.md c79ed3c verified

Create README.md 3fec8ed verified

Upload folder using huggingface_hub 4b88149 verified

initial commit 6c104e4 verified

Update README.md

b2491b2
verified

Upload 2 files

6bc2515
verified

Update README.md

ede6d36
verified

Update README.md

39b96eb
verified

Update README.md

11d7026
verified

Update README.md

7588ed0
verified

Add model metadata and links to paper and code (#1)

c3ff880

Update README.md

8e74169
verified

Update README.md

6ed17a3
verified

Update README.md

ae3a39f
verified

Update README.md

c79ed3c
verified

Create README.md

3fec8ed
verified

Upload folder using huggingface_hub

4b88149
verified

initial commit

6c104e4
verified