Environment variables

Some environment variables can be configured to customize the execution. When using Python, these variables should be set before importing the ctranslate2 module, e.g.:

import os
os.environ["CT2_VERBOSE"] = "1"

import ctranslate2

Note

Boolean environment variables can be enabled with "1" or "true".

CT2_CUDA_ALLOCATOR

Allocating memory on the GPU with cudaMalloc is costly and is best avoided in high-performance code. For this reason CTranslate2 integrates caching allocators which enable a fast reuse of previously allocated buffers. The following allocators are integrated:

CT2_CUDA_ALLOW_FP16

Allow using FP16 computation on GPU even if the device does not have efficient FP16 support.

CT2_CUDA_CACHING_ALLOCATOR_CONFIG

The cub_caching allocator can be configured to tradeoff memory usage and speed. By default, CTranslate2 uses the following values which have been selected experimentally:

  • bin_growth = 4

  • min_bin = 3

  • max_bin = 12

  • max_cached_bytes = 209715200 (200MB)

You can override these parameters with comma-separated values in the same order as the list above:

export CT2_CUDA_CACHING_ALLOCATOR_CONFIG=8,3,7,6291455

See the description of each parameter in the allocator implementation.

CT2_FORCE_CPU_ISA

Force CTranslate2 to select a specific instruction set architecture (ISA). Possible values are:

  • GENERIC

  • AVX

  • AVX2

Attention

This does not impact backend libraries (such as Intel MKL) which usually have their own environment variables to configure ISA dispatching.

CT2_TRANSLATORS_CORE_OFFSET

If set to a non negative value, parallel translators are pinned to CPU cores in the range [offset, offset + inter_threads].

Requires compiling with -DOPENMP_RUNTIME=NONE.

CT2_USE_EXPERIMENTAL_PACKED_GEMM

Enable the packed GEMM API for Intel MKL which can improve performance for single-core decoding. See Intel’s article to learn more about packed GEMM.

CT2_USE_MKL

Force CTranslate2 to use (or not) Intel MKL. By default, the runtime automatically decides whether to use Intel MKL or not based on the CPU vendor.

CT2_VERBOSE

Configure the logs verbosity:

  • -3 = off

  • -2 = critical

  • -1 = error

  • 0 = warning (default)

  • 1 = info

  • 2 = debug

  • 3 = trace