Transformer Engine documentation

Warning

You are currently viewing unstable developer preview of the documentation. To see the documentation for the latest stable release, refer to:

Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. TE also includes a framework agnostic C++ API that can be integrated with other deep learning libraries to enable FP8 support for Transformers.

As the number of parameters in Transformer models continues to grow, training and inference for architectures such as BERT, GPT and T5 become very memory and compute-intensive. Most deep learning frameworks train with FP32 by default. This is not essential, however, to achieve full accuracy for many deep learning models. Using mixed-precision training, which combines single-precision (FP32) with lower precision (e.g. FP16) format when training a model, results in significant speedups with minimal differences in accuracy as compared to FP32 training. With Hopper GPU architecture FP8 precision was introduced, which offers improved performance over FP16 with no degradation in accuracy. Although all major deep learning frameworks support FP16, FP8 support is not available natively in frameworks today.

TE addresses the problem of FP8 support by providing APIs that integrate with popular Large Language Model (LLM) libraries. It provides a Python API consisting of modules to easily build a Transformer layer as well as a framework-agnostic library in C++ including structs and kernels needed for FP8 support. Modules provided by TE internally maintain scaling factors and other values needed for FP8 training, greatly simplifying mixed precision training for users.

Highlights

  • Easy-to-use modules for building Transformer layers with FP8 support

  • Optimizations (e.g. fused kernels) for Transformer models

  • Support for FP8 on NVIDIA Hopper and NVIDIA Ada GPUs

  • Support for optimizations across all precisions (FP16, BF16) on NVIDIA Ampere GPU architecture generations and later

Examples

PyTorch

import torch
import transformer_engine.pytorch as te
from transformer_engine.common import recipe

# Set dimensions.
in_features = 768
out_features = 3072
hidden_size = 2048

# Initialize model and inputs.
model = te.Linear(in_features, out_features, bias=True)
inp = torch.randn(hidden_size, in_features, device="cuda")

# Create an FP8 recipe. Note: All input args are optional.
fp8_recipe = recipe.DelayedScaling(margin=0, interval=1, fp8_format=recipe.Format.E4M3)

# Enable autocasting for the forward pass
with te.fp8_autocast(enabled=True, fp8_recipe=fp8_recipe):
    out = model(inp)

loss = out.sum()
loss.backward()

JAX

Flax

import jax
import jax.numpy as jnp
import transformer_engine.jax as te
import transformer_engine.jax.flax as te_flax
from transformer_engine.common import recipe

BATCH = 32
SEQLEN = 128
HIDDEN = 1024

# Initialize RNG and inputs.
rng = jax.random.PRNGKey(0)
init_rng, data_rng = jax.random.split(rng)
inp = jax.random.normal(data_rng, [BATCH, SEQLEN, HIDDEN], jnp.float32)

# Create an FP8 recipe. Note: All input args are optional.
fp8_recipe = recipe.DelayedScaling(margin=0, interval=1, fp8_format=recipe.Format.HYBRID)

# Enable autocasting for the forward pass
with te.fp8_autocast(enabled=True, fp8_recipe=fp8_recipe):
    model = te_flax.DenseGeneral(features=HIDDEN)

    def loss_fn(params, other_vars, inp):
      out = model.apply({'params':params, **other_vars}, inp)
      return jnp.mean(out)

    # Initialize models.
    variables = model.init(init_rng, inp)
    other_variables, params = variables.pop('params')

    # Construct the forward and backward function
    fwd_bwd_fn = jax.value_and_grad(loss_fn, argnums=(0, 1))

    for _ in range(10):
      loss, (param_grads, other_grads) = fwd_bwd_fn(params, other_variables, inp)