Model Architecture: granite-3.1-8b-base
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: FP8
- Activation quantization: FP8
Release Date: 1/8/2025
Version: 1.0
Model Developers: Neural Magic

Quantized version of ibm-granite/granite-3.1-8b-base. It achieves an average score of 66.94 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 67.44.

Model Optimizations

This model was obtained by quantizing the weights and activations of ibm-granite/granite-3.1-8b-base to FP8 data type, ready for inference with vLLM >= 0.5.2. 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.

Deployment

Use with vLLM

This model can be deployed efficiently using the vLLM backend, as shown in the example below.

python

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

max_model_len, tp_size = 4096, 1
model_name = "neuralmagic/granite-3.1-8b-base-FP8-dynamic"
tokenizer = AutoTokenizer.from_pretrained(model_name)
llm = LLM(model=model_name, tensor_parallel_size=tp_size, max_model_len=max_model_len, trust_remote_code=True)
sampling_params = SamplingParams(temperature=0.3, max_tokens=256, stop_token_ids=[tokenizer.eos_token_id])

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)

vLLM also supports OpenAI-compatible serving. See the documentation for more details.

Creation

This model was created with llm-compressor by running the code snippet below.

Model Creation Code

python quantize.py --model_id ibm-granite/granite-3.1-8b-base --save_path "output_dir/"

python

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

def main():
    parser = argparse.ArgumentParser(description='Quantize a transformer model to FP8')
    parser.add_argument('--model_id', type=str, required=True,
                        help='The model ID from HuggingFace (e.g., "meta-llama/Meta-Llama-3-8B-base")')
    parser.add_argument('--save_path', type=str, default='.',
                        help='Custom path to save the quantized model. If not provided, will use model_name-FP8-dynamic')
    args = parser.parse_args()

    # Load model
    model = AutoModelForCausalLM.from_pretrained(
        args.model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True,
    )
    tokenizer = AutoTokenizer.from_pretrained(args.model_id)

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

    # Apply quantization
    oneshot(model=model, recipe=recipe)

    save_path = os.path.join(args.save_path, args.model_id.split("/")[1] + "-FP8-dynamic")
    os.makedirs(save_path, exist_ok=True)

    # Save to disk in compressed-tensors format
    model.save_pretrained(save_path)
    tokenizer.save_pretrained(save_path)
    print(f"Model and tokenizer saved to: {save_path}")

if __name__ == "__main__":
    main()

Evaluation

The model was evaluated on OpenLLM Leaderboard V1, OpenLLM Leaderboard V2 and on HumanEval, using the following commands:

Evaluation Commands

OpenLLM Leaderboard V1:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/granite-3.1-8b-base-FP8-dynamic",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks openllm \
  --write_out \
  --batch_size auto \
  --output_path output_dir \
  --show_config

HumanEval

Generation

python3 codegen/generate.py \
  --model neuralmagic/granite-3.1-8b-base-FP8-dynamic \
  --bs 16 \
  --temperature 0.2 \
  --n_samples 50 \
  --root "." \
  --dataset humaneval

Sanitization

python3 evalplus/sanitize.py \
  humaneval/neuralmagic--granite-3.1-8b-base-FP8-dynamic_vllm_temp_0.2

Evaluation

evalplus.evaluate \
  --dataset humaneval \
  --samples humaneval/neuralmagic--granite-3.1-8b-base-FP8-dynamic_vllm_temp_0.2-sanitized

Accuracy

Category	Metric	ibm-granite/granite-3.1-8b-base	neuralmagic/granite-3.1-8b-base-FP8-dynamic	Recovery (%)
OpenLLM V1	ARC-Challenge (Acc-Norm, 25-shot)	64.68	64.16	99.20
GSM8K (Strict-Match, 5-shot)	60.88	58.45	95.99
HellaSwag (Acc-Norm, 10-shot)	83.52	83.46	99.93
MMLU (Acc, 5-shot)	63.33	63.35	100.03
TruthfulQA (MC2, 0-shot)	51.33	51.56	100.45
Winogrande (Acc, 5-shot)	80.90	80.66	99.70
Average Score	67.44	66.94	99.26
Coding	HumanEval Pass@1	44.10	44.80	101.59

Inference Performance

This model achieves up to 1.5x speedup in single-stream deployment and up to 1.1x speedup in multi-stream asynchronous deployment on L40 GPUs. The following performance benchmarks were conducted with vLLM version 0.6.6.post1, and GuideLLM.

Benchmarking Command

guidellm --model neuralmagic/granite-3.1-8b-base-FP8-dynamic --target "http://localhost:8000/v1" --data-type emulated --data "prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>" --max seconds 360 --backend aiohttp_server

Single-stream performance (measured with vLLM version 0.6.6.post1)

GPU class	Model	Speedup	Code Completion prefill: 256 tokens decode: 1024 tokens	Docstring Generation prefill: 768 tokens decode: 128 tokens	Code Fixing prefill: 1024 tokens decode: 1024 tokens	RAG prefill: 1024 tokens decode: 128 tokens	Instruction Following prefill: 256 tokens decode: 128 tokens	Multi-turn Chat prefill: 512 tokens decode: 256 tokens	Large Summarization prefill: 4096 tokens decode: 512 tokens
			Latency (s)
L40	granite-3.1-8b-base		25.1	3.2	25.3	3.2	3.2	6.3	13.4
granite-3.1-8b-base-FP8-dynamic (this model)	1.47	16.8	2.2	17.1	2.2	2.1	4.2	9.3
granite-3.1-8b-base-quantized.w4a16	2.72	8.9	1.2	9.2	1.2	1.1	2.3	5.3

Multi-stream asynchronous performance (measured with vLLM version 0.6.6.post1)

GPU class	Model	Speedup	Code Completion prefill: 256 tokens decode: 1024 tokens	Docstring Generation prefill: 768 tokens decode: 128 tokens	Code Fixing prefill: 1024 tokens decode: 1024 tokens	RAG prefill: 1024 tokens decode: 128 tokens	Instruction Following prefill: 256 tokens decode: 128 tokens	Multi-turn Chat prefill: 512 tokens decode: 256 tokens	Large Summarization prefill: 4096 tokens decode: 512 tokens
			Maximum Throughput (Queries per Second)
L40	granite-3.1-8b-base		1.4	7.8	1.1	6.2	15.5	6.0	0.7
granite-3.1-8b-base-FP8-dynamic (this model)	1.12	2.1	7.4	1.3	5.9	15.3	6.9	0.8
granite-3.1-2b-base-quantized.w4a16	1.29	2.4	8.9	1.4	7.1	17.8	7.8	1.0

RedHatAI/granite-3.1-8b-base-FP8-dynamic

granite-3.1-8b-base-FP8-dynamic

Model Overview

Model Optimizations

Deployment

Use with vLLM

Creation

Evaluation

HumanEval

Generation

Sanitization

Evaluation

Accuracy

Inference Performance

Single-stream performance (measured with vLLM version 0.6.6.post1)

Multi-stream asynchronous performance (measured with vLLM version 0.6.6.post1)

RedHatAI/
granite-3.1-8b-base-FP8-dynamic