VLLM_USE_MODELSCOPE=True vllm serve Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 \
  --enable-expert-parallel \
  --data-parallel-size 8 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3-coder

from modelscope import AutoProcessor, AutoModelForCausalLM
import torch
model_name = "Shanghai_AI_Laboratory/Intern-S1"
processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "tell me about an interesting physical phenomenon."},
        ],
    }
]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
generate_ids = model.generate(**inputs, max_new_tokens=32768)
decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
print(decoded_output)

from modelscope import AutoProcessor, AutoModelForCausalLM
import torch
model_name = "Shanghai_AI_Laboratory/Intern-S1"
processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
            {"type": "text", "text": "Please describe the image explicitly."},
        ],
    }
]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)
generate_ids = model.generate(**inputs, max_new_tokens=32768)
decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
print(decoded_output)

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B-Instruct-2507 --tp 8 --context-length 262144

VLLM_USE_MODELSCOPE=true vllm serve Qwen/Qwen3-235B-A22B-Instruct-2507 --tensor-parallel-size 8 --max-model-len 262144

SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B-Thinking-2507 --tp 8 --context-length 262144  --reasoning-parser deepseek-r1

VLLM_USE_MODELSCOPE=true vllm serve Qwen/Qwen3-235B-A22B-Thinking-2507 --tensor-parallel-size 8 --max-model-len 262144 --enable-reasoning --reasoning-parser deepseek_r1

from modelscope import AutoTokenizer, AutoModelForCausalLM
model_name = "Kwaipilot/KAT-V1-40B"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=65536,
    temperature=0.6,
    top_p=0.95,
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 
content = tokenizer.decode(output_ids, skip_special_tokens=True).strip("\n")
print("prompt:\n", prompt)
print("content:\n", content)
"""
prompt:
Give me a short introduction to large language model.
content:
<judge>
The user's request is to provide a concise factual introduction to large language models, which involves retrieving and summarizing basic information. This task is straightforward as it only requires recalling and presenting well-known details without deeper analysis. No complex reasoning is needed here—just a simple explanation will suffice.
</judge>
<think_off>
<answer>
A **Large Language Model (LLM)** is an advanced AI system trained on vast amounts of text data to understand, generate, and process human-like language. Here’s a concise introduction:
### Key Points:
1. **Training**: Trained on diverse text sources (books, websites, etc.) using deep learning.
2. **Capabilities**: 
   - Answer questions, generate text, summarize content, translate languages.
   - Understand context, sentiment, and nuances in language.
3. **Architecture**: Often based on **transformer models** (e.g., BERT, GPT, LLaMA).
4. **Scale**: Billions of parameters, requiring massive computational resources.
5. **Applications**: Chatbots, content creation, coding assistance, research, and more.
### Examples:
- **OpenAI’s GPT-4**: Powers ChatGPT.
- **Google’s Gemini**: Used in Bard.
- **Meta’s LLaMA**: Open-source alternative.
### Challenges:
- **Bias**: Can reflect biases in training data.
- **Accuracy**: May hallucinate "facts" not grounded in reality.
- **Ethics**: Raises concerns about misinformation and job displacement.
LLMs represent a leap forward in natural language processing, enabling machines to interact with humans in increasingly sophisticated ways. 🌐🤖
</answer>
"""