Qwen3-Coder-Next

# Update the vllm-ascend image
# For Atlas A2 machines:
# export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|
# For Atlas A3 machines:
export IMAGE=quay.io/ascend/vllm-ascend:|vllm_ascend_version|-a3
docker run --rm \
--shm-size=1g \
--name qwen3-coder-next \
--device /dev/davinci0 \
--device /dev/davinci1 \
--device /dev/davinci2 \
--device /dev/davinci3 \
--device /dev/davinci_manager \
--device /dev/devmm_svm \
--device /dev/hisi_hdc \
-v /usr/local/dcmi:/usr/local/dcmi \
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
-v /usr/local/Ascend/driver/lib64/:/usr/local/Ascend/driver/lib64/ \
-v /usr/local/Ascend/driver/version.info:/usr/local/Ascend/driver/version.info \
-v /etc/ascend_install.info:/etc/ascend_install.info \
-v /root/.cache:/root/.cache \
-p 8000:8000 \
-it $IMAGE bash

pip install triton-ascend==3.2.0

import os
os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"

from vllm import LLM, SamplingParams


def main():
    prompts = [
        "Hello, my name is",
        "The president of the United States is",
        "The capital of France is",
        "The future of AI is",
    ]

    # Create a sampling params object.
    sampling_params = SamplingParams(max_tokens=100, temperature=0.0)
    # Create an LLM.
    llm = LLM(model="/path/to/model/Qwen3-Coder-Next/",
            tensor_parallel_size=4,
            trust_remote_code=True,
            max_model_len=10000,
            gpu_memory_utilization=0.8,
            max_num_seqs=4,
            max_num_batched_tokens = 4096,
            compilation_config={
            "cudagraph_mode": "FULL_DECODE_ONLY",},
        )

    # Generate texts from the prompts.
    outputs = llm.generate(prompts, sampling_params)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")


if __name__ == "__main__":
    main()

vllm serve /path/to/model/Qwen3-Coder-Next/ --tensor-parallel-size 4 --max-model-len 32768 --gpu-memory-utilization 0.8 --max-num-batched-tokens 4096 --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY"}'

curl http://localhost:8000/v1/completions \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "The future of AI is",
        "path": "/path/to/model/Qwen3-Coder-Next/",
        "max_tokens": 100,
        "temperature": 0
        }'

Prompt: 'The future of AI is', Generated text: ' not just about building smarter machines, but about creating systems that can collaborate with humans in meaningful, ethical, and sustainable ways. As AI continues to evolve, it will increasingly shape how we live, work, and interact — and the decisions we make today will determine whether this future is one of shared prosperity or deepening inequality.\n\nThe rise of generative AI, for example, has already begun to transform creative industries, education, and scientific research. Tools like ChatGPT, Midjourney, and'