Qwen3-8B-FP8-dynamic

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Qwen3-8B-FP8-dynamic"
number_gpus = 1
sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=20, min_p=0, max_tokens=256)

messages = [
    {"role": "user", "content": prompt}
]

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

from llmcompressor.modifiers.quantization import QuantizationModifier
  from llmcompressor.transformers import oneshot
  from transformers import AutoModelForCausalLM, AutoTokenizer
  
  # Load model
  model_stub = "Qwen/Qwen3-8B"
  model_name = model_stub.split("/")[-1]

  model = AutoModelForCausalLM.from_pretrained(model_stub)

  tokenizer = AutoTokenizer.from_pretrained(model_stub)

  # Configure the quantization algorithm and scheme
  recipe = QuantizationModifier(
      ignore=["lm_head"],
      targets="Linear",
      scheme="FP8_dynamic",
  )

  # Apply quantization
  oneshot(
      model=model,
      recipe=recipe,
  )
  
  # Save to disk in compressed-tensors format
  save_path = model_name + "-FP8-dynamic"
  model.save_pretrained(save_path)
  tokenizer.save_pretrained(save_path)
  print(f"Model and tokenizer saved to: {save_path}")