CTranslate2 Files

Fast inference engine for Transformer models

This is an exact mirror of the CTranslate2 project, hosted at https://github.com/OpenNMT/CTranslate2. SourceForge is not affiliated with CTranslate2.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
rocm-python-wheels-Linux.zip	2026-11-10	431.2 MB	0
rocm-python-wheels-Windows.zip	2026-11-10	194.0 MB	0
README.md	2026-11-10	1.0 kB	0
v4.9.0 source code.tar.gz	2026-11-10	3.7 MB	0
v4.9.0 source code.zip	2026-11-10	4.0 MB	2
Totals: 5 Items		632.9 MB	2

New features

Add an experimental Apple Metal (MPS) backend for Apple Silicon GPUs, selected with device="mps" (#2077) by @TBO22. It is included in Apple Silicon Python wheels and can be enabled in source builds with -DWITH_MPS=ON; device="auto" continues to select CPU on Apple Silicon
Include gfx1031, gfx1032, gfx1035, and gfx1103 targets in the ROCm wheels (#2142) by @jordimas

Fixes and improvements

Scale rotary embeddings in float32 before the dtype conversion to preserve precision in FP16 and BF16 models (#2146) by @Kyozzz
Replace the deprecated FindCUDA CMake module with native CMake CUDA support (#2067) by @gaborlukacs
Bump the CI MKL to 2025.3 and reuse shared build scripts (#2145) by @jordimas
Add performance and accuracy regression tests to CI (#2147) by @jordimas

Source: README.md, updated 2026-11-10

Other Useful Business Software

Cut Data Warehouse Costs by 54% Icon

Cut Data Warehouse Costs by 54%

Easily migrate from Snowflake, Redshift, or Databricks with free tools.

BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.

Start Free

Go from Code to Production URL in Seconds Icon

Go from Code to Production URL in Seconds

Cloud Run deploys apps in any language instantly. Scales to zero. Pay only when code runs.

Skip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.

Start Free

$300 Free Credits to Build on Google Cloud

New customers can spin up VMs, build with AI, and query data at no cost.

Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.

Start Free

Recommended Projects

Transformer Explainer
Learn How LLM Transformer Models Work with Interactive Visualization
BitNet
BitNet: Scaling 1-bit Transformers for Large Language Models
SageAttention
NeurIPS2025 Spotlight] Quantized Attention
picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy
Text Generation Web UI
Oobabooga - The definitive Web UI for local AI, with powerful features