FP8 Quantization

We recommend using FP8 quantization for dedicated models which allows for a 2x reduction in model memory requirements and up to 1.6x improvement in inference speed with minimal impact on accuracy.

The easiest and recommended way to quantize the model is using llm-compressor with FP8_DYNAMIC scheme. In this setting, there is no need for any calibration data since the activations are quantized dynamically.

Here is an example of how to use llm-compressor to quantize a model:

# pip install llmcompressor

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

MODEL_ID = "YOUR_HUGGINGFACE_MODEL_HERE"

# Load model
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID, device_map="auto", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

# Apply quantization.
recipe = QuantizationModifier(
    targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]
)
oneshot(model=model, recipe=recipe)

# Confirm generations of the quantized model look sane.
print("========== SAMPLE GENERATION ==============")
input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
output = model.generate(input_ids, max_new_tokens=20)
print(tokenizer.decode(output[0]))
print("==========================================")

# Save to disk in compressed-tensors format
save_path = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")