Llama 4 Scout 17B 16E Instruct FP8 Dynamic

🚀 Llama-4-Scout-17B-16E-Instruct-FP8-dynamic

Built with Llama, this model offers efficient text and image processing with optimized quantization techniques.

🚀 Quick Start

This model can be deployed efficiently using the vLLM backend. Here is an example:

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
number_gpus = 4

sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

prompt = "Give me a short introduction to large language model."

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

outputs = llm.generate(prompt, sampling_params)

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

✨ Features

Model Overview

• Model Architecture: Llama4ForConditionalGeneration
  • Input: Text / Image
  • Output: Text
• Model Optimizations:
  • Activation quantization: FP8
  • Weight quantization: FP8
• Release Date: 04/15/2025
• Version: 1.0
• Model Developers: Red Hat (Neural Magic)

Model Optimizations

This model was obtained by quantizing activations and weights of Llama-4-Scout-17B-16E-Instruct to FP8 data type. This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). Weight quantization also reduces disk size requirements by approximately 50%. The llm-compressor library is used for quantization.

💻 Usage Examples

Basic Usage

The basic usage of this model is demonstrated in the deployment example above.

Advanced Usage

The following code shows how to create the model with llm-compressor:

#!/usr/bin/env python3
"""
This script loads an LLM model and applies FP8 quantization to
weights and activations. Activations are dynamically quantized, i.e. during
actual runtime.
"""

import argparse
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, Llama4ForConditionalGeneration
from llmcompressor.modifiers.quantization import QuantizationModifier
from llmcompressor import oneshot
from compressed_tensors.quantization import (
    QuantizationScheme,
    QuantizationArgs,
    QuantizationType,
    QuantizationStrategy,
)


def parse_arguments():
    """Parse command line arguments."""
    parser = argparse.ArgumentParser(description="Quantize a causal language model")
    parser.add_argument(
        "--model_path",
        type=str,
        required=True,
        help="Path to the pre-trained model",
    )
    parser.add_argument(
        "--quant_path",
        type=str,
        required=True,
        help="Output path for the quantized model",
    )
    return parser.parse_args()


def main():
    """Main function to load and quantize the model."""
    args = parse_arguments()

    print(f"Loading model from {args.model_path}...")
    model = Llama4ForConditionalGeneration.from_pretrained(
        args.model_path,
        device_map="auto",
        torch_dtype="auto",
        trust_remote_code=True,
    )

    quant_scheme = QuantizationScheme(
        targets=["Linear"],
        weights=QuantizationArgs(
            num_bits=8,
            type=QuantizationType.FLOAT,
            strategy=QuantizationStrategy.CHANNEL,
            symmetric=True,
            observer="mse",
        ),
        input_activations=QuantizationArgs(
            num_bits=8,
            type=QuantizationType.FLOAT,
            strategy=QuantizationStrategy.TOKEN,
            symmetric=True,
            dynamic=True,
        ),
        output_activations=None,
    )

    recipe = QuantizationModifier(
        targets="Linear",
        config_groups={"group_0": quant_scheme},
        ignore=[
            're:.*lm_head',
            're:.*self_attn',
            're:.*router',
            're:.*vision_model',
            're:.*multi_modal_projector',
        ]
    )

    print("Applying quantization...")
    oneshot(
        model=model,
        recipe=recipe,
        trust_remote_code_model=True,
    )

    model.save_pretrained(args.quant_path, save_compressed=True, skip_compression_stats=True, disable_sparse_compression=True)
    print(f"Quantized model saved to {args.quant_path}")


if __name__ == "__main__":
    main()

📚 Documentation

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks (v1 and v2), long context RULER, multimodal MMMU, and multimodal ChartQA. All evaluations are obtained through lm-evaluation-harness.

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=8,gpu_memory_utilization=0.7,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --batch_size auto 

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic",dtype=auto,add_bos_token=False,max_model_len=16384,tensor_parallel_size=8,gpu_memory_utilization=0.5,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks leaderboard \
  --apply_chat_template \
  --fewshot_as_multiturn \
  --batch_size auto 

lm_eval \
  --model vllm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic",dtype=auto,add_bos_token=False,max_model_len=524288,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks ruler \
  --metadata='{"max_seq_lengths":[131072]}' \
  --batch_size auto 

lm_eval \
  --model vllm-vlm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic",dtype=auto,add_bos_token=False,max_model_len=1000000,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True,max_images=10 \
  --tasks mmmu_val \
  --apply_chat_template \
  --batch_size auto 

export VLLM_MM_INPUT_CACHE_GIB=8
lm_eval \
  --model vllm-vlm \
  --model_args pretrained="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic",dtype=auto,add_bos_token=False,max_model_len=1000000,tensor_parallel_size=8,gpu_memory_utilization=0.9,enable_chunked_prefill=True,trust_remote_code=True,max_images=10 \
  --tasks chartqa \
  --apply_chat_template \
  --batch_size auto 

Accuracy

📄 License

The license for this model is under the "other" category, with the license name being "llama4".