vLLM supports FP8 (8-bit floating point) weight and activation quantization using hardware acceleration on GPUs such as Nvidia H100 and AMD MI300x.
Currently, only Hopper and Ada Lovelace GPUs are supported.
Quantization of models with FP8 allows for a 2x reduction in model memory requirements and up to a 1.6x improvement in throughput with minimal impact on accuracy.
Please visit the HF collection of `quantized FP8 checkpoints of popular LLMs ready to use with vLLM <https://huggingface.co/collections/neuralmagic/fp8-llms-for-vllm-666742ed2b78b7ac8df13127>`_.
The FP8 types typically supported in hardware have two distinct representations, each useful in different scenarios:
-**E4M3**: Consists of 1 sign bit, 4 exponent bits, and 3 bits of mantissa. It can store values up to +/-448 and ``nan``.
-**E5M2**: Consists of 1 sign bit, 5 exponent bits, and 2 bits of mantissa. It can store values up to +/-57344, +/- ``inf``, and ``nan``. The tradeoff for the increased dynamic range is lower precision of the stored values.
Dynamic quantization of an original precision BF16/FP16 model to FP8 can be achieved with vLLM without any calibration data required. You can enable the feature by specifying ``--quantization="fp8"`` in the command line or setting ``quantization="fp8"`` in the LLM constructor.
In this mode, all Linear modules (except for the final ``lm_head``) have their weights quantized down to FP8_E4M3 precision with a per-tensor scale. Activations have their minimum and maximum values calculated during each forward pass to provide a dynamic per-tensor scale for high accuracy. As a result, latency improvements are limited in this mode.
..code-block:: python
from vllm import LLM
model = LLM("facebook/opt-125m", quantization="fp8")
# INFO 06-10 17:55:42 model_runner.py:157] Loading model weights took 0.1550 GB
result = model.generate("Hello, my name is")
..warning::
Currently, we load the model at original precision before quantizing down to 8-bits, so you need enough memory to load the whole model.
Offline Quantization
--------------------
For offline quantization to FP8, please install the `AutoFP8 library <https://github.com/neuralmagic/autofp8>`_.
You can use AutoFP8 to produce checkpoints with their weights quantized to FP8 ahead of time and let vLLM handle calculating dynamic scales for the activations at runtime for maximum accuracy. You can enable this with the ``activation_scheme="dynamic"`` argument.
..warning::
Please note that although this mode doesn't give you better performance, it reduces memory footprint compared to online quantization.
..code-block:: python
from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
For the best inference performance, you can use AutoFP8 with calibration data to produce per-tensor static scales for both the weights and activations by enabling the ``activation_scheme="static"`` argument.
..code-block:: python
from datasets import load_dataset
from transformers import AutoTokenizer
from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
Additionally, there can be `FP8 kv-cache scaling factors <https://github.com/vllm-project/vllm/pull/4893>`_ contained within quantized checkpoints specified through the ``.kv_scale`` parameter present on the Attention Module, such as:
