Read our blog post for a detailed treatment of how quantization affects model quality.
Checking available precisions
Models may support different numerical precisions like FP16, FP8, BF16, or INT8, which affect memory usage and inference speed. Check default precision:Precisions field indicates what precisions the model has been prepared for.
Quantizing a model
A model can be quantized to 8-bit floating-point (FP8) precision.- firectl
- Python (REST API)
This is an additive process that enables creating deployments with additional precisions. The original FP16 checkpoint is still available for use.
- firectl
- Python (REST API)
PREPARING. A successfully prepared model will have the desired precision added
to the Precisions list.
Creating an FP8 deployment
By default, creating a deployment uses the FP16 checkpoint. To use a quantized FP8 checkpoint, first ensure the model has been prepared for FP8 (see Checking available precisions above), then pass the--precision flag when creating your deployment:
- firectl
- Python (REST API)
Quantized deployments can only be served using H100 GPUs.