Instructions to use Qwen/Qwen3-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-30B-A3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-30B-A3B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use Qwen/Qwen3-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen3-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-30B-A3B

SGLang

How to use Qwen/Qwen3-30B-A3B 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 "Qwen/Qwen3-30B-A3B" \
    --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": "Qwen/Qwen3-30B-A3B",
		"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 "Qwen/Qwen3-30B-A3B" \
        --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": "Qwen/Qwen3-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-30B-A3B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-30B-A3B
```

KeyError: 'rope_type'

by yuchenxie - opened Apr 29, 2025

Discussion

yuchenxie

Apr 29, 2025

Command used:

CUDA_VISIBLE_DEVICES=0,2 vllm serve Qwen/Qwen3-30B-A3B -tp 2 --enable-reasoning --reasoning-parser deepseek_r1 --rope-scaling '{"type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072 --gpu-memory-utilization 0.97

Error + full traceback:

INFO 04-28 18:14:25 [config.py:456] Overriding HF config with {'rope_scaling': {'type': 'yarn', 'factor': 4.0, 'original_max_position_embeddings': 32768}}
Traceback (most recent call last):
  File "/root/anaconda3/envs/trainer/bin/vllm", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/entrypoints/cli/main.py", line 53, in main
    args.dispatch_function(args)
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/entrypoints/cli/serve.py", line 27, in cmd
    uvloop.run(run_server(args))
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/uvloop/__init__.py", line 105, in run
    return runner.run(wrapper())
           ^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper
    return await main
           ^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 1078, in run_server
    async with build_async_engine_client(args) as engine_client:
  File "/root/anaconda3/envs/trainer/lib/python3.11/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 146, in build_async_engine_client
    async with build_async_engine_client_from_engine_args(
  File "/root/anaconda3/envs/trainer/lib/python3.11/contextlib.py", line 210, in __aenter__
    return await anext(self.gen)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 166, in build_async_engine_client_from_engine_args
    vllm_config = engine_args.create_engine_config(usage_context=usage_context)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/engine/arg_utils.py", line 1099, in create_engine_config
    model_config = self.create_model_config()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/engine/arg_utils.py", line 987, in create_model_config
    return ModelConfig(
           ^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/config.py", line 508, in __init__
    self.max_model_len = _get_and_verify_max_len(
                         ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/anaconda3/envs/trainer/lib/python3.11/site-packages/vllm/config.py", line 3054, in _get_and_verify_max_len
    rope_type = rope_scaling["rope_type"]
                ~~~~~~~~~~~~^^^^^^^^^^^^^
KeyError: 'rope_type'

CaryH

Apr 29, 2025

change --rope-scaling '{"type":"yarn"... to --rope-scaling '{"rope_type":"yarn"...

jklj077 changed discussion status to closed Apr 30, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment