Instructions to use z-lab/Qwen3.6-27B-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use z-lab/Qwen3.6-27B-DFlash with Transformers:

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

pipe = pipeline("text-generation", model="z-lab/Qwen3.6-27B-DFlash", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("z-lab/Qwen3.6-27B-DFlash", trust_remote_code=True)
model = AutoModel.from_pretrained("z-lab/Qwen3.6-27B-DFlash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use z-lab/Qwen3.6-27B-DFlash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/Qwen3.6-27B-DFlash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/Qwen3.6-27B-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/z-lab/Qwen3.6-27B-DFlash

SGLang

How to use z-lab/Qwen3.6-27B-DFlash 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 "z-lab/Qwen3.6-27B-DFlash" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/Qwen3.6-27B-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "z-lab/Qwen3.6-27B-DFlash" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/Qwen3.6-27B-DFlash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use z-lab/Qwen3.6-27B-DFlash with Docker Model Runner:
```
docker model run hf.co/z-lab/Qwen3.6-27B-DFlash
```

FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:

#18

by MavisFace - opened about 1 month ago

Discussion

MavisFace

about 1 month ago

This error spams, and I've tried various launch codes...Kimi K2.6 says the model is not made for the DGX Spark GB10 architecture...I'm a noob. Did I install a dependency wrong? I have my own custom venv just for this model using the modified vLLM.

FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:
FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:
FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:
FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:
FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:
FlashAttention requires building with sm version sm80-sm90, but was built for < 8.0!FATAL:

MavisFace

29 days ago

This was a bonehead mistake on my part. A real test is coming on NVIDIA DGX Spark. Reporting back with results within 48 hours.

MavisFace

19 days ago

making a new thread cuz I forgot to activate the venv and basically just ruined my stack and had to reinstall a lot of things again lol.....

MavisFace changed discussion status to closed 19 days ago

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