Qwq 32B FP8 Dynamic

🚀 QwQ-32B-FP8-dynamic

A quantized version of Qwen/QwQ-32B with efficient deployment capabilities.

🚀 Quick Start

This model can be deployed efficiently using the vLLM backend. Check out the usage examples below for details.

✨ Features

• Model Architecture: Qwen2ForCausalLM, taking text as input and outputting text.
• Model Optimizations:
  • Weight quantization: FP8
  • Activation quantization: FP8
• Release Date: 3/6/2025
• Version: 1.0
• Model Developers: Neural Magic

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

number_gpus = 1
model_name = "neuralmagic/QwQ-32B-FP8-dynamic"

tokenizer = AutoTokenizer.from_pretrained(model_name)
sampling_params = SamplingParams(temperature=0.6, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])
llm = LLM(model=model_name, tensor_parallel_size=number_gpus, trust_remote_code=True)

messages_list = [
    [{"role": "user", "content": "Who are you? Please respond in pirate speak!"}],
]

prompt_token_ids = [tokenizer.apply_chat_template(messages, add_generation_prompt=True) for messages in messages_list]

outputs = llm.generate(prompt_token_ids=prompt_token_ids, sampling_params=sampling_params)

generated_text = [output.outputs[0].text for output in outputs]
print(generated_text)

Advanced Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor.transformers import oneshot
import os

# Load model
model_stub = "Qwen/QwQ-32B"
model_name = model_stub.split("/")[-1]

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    torch_dtype="auto",
)

tokenizer = AutoTokenizer.from_pretrained(model_stub)

# Configure the quantization algorithm and scheme
recipe = QuantizationModifier(
    targets="Linear",
    scheme="FP8_DYNAMIC",
    ignore=["lm_head"],
)

# 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}")

📚 Documentation

Model Optimizations

This model was obtained by quantizing the weights and activations of Qwen/QwQ-32B to FP8 data type. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.

Only the weights and activations of the linear operators within transformers blocks are quantized. Weights are quantized using a symmetric per-channel scheme, whereas quantizations are quantized using a symmetric per-token scheme. LLM Compressor is used for quantization.

Accuracy

🔧 Technical Details

The model uses LLM Compressor for quantization. The weights are quantized using a symmetric per-channel scheme, and the activations are quantized using a symmetric per-token scheme.

📄 License

This project is licensed under the MIT license.