PyTorch Tokenizers
JSON →PyTorch-Tokenizers is a Python package providing efficient C++ implementations for common tokenizers like SentencePiece and TikToken, along with Python bindings. It is primarily designed to serve as a dependency for other PyTorch projects, such as ExecuTorch and torchchat, to facilitate building high-performance LLM runners. The library offers significant efficiency gains for AI workloads, multilingual support, and high decode accuracy. It is actively maintained, with version 1.2.0 aligning its releases with major PyTorch and ExecuTorch updates.
Traffic · last 30 days ↓22% vs prev 7d
total hits 18
actors 6 distinct systems
last hit 3d ago MetaBot
top countries 🇺🇸 United States · 🇩🇪 Germany · 🇨🇦 Canada · 🇫🇷 France · 🇮🇹 Italy
Resources
homepagepytorch.org/executorch/ ↗
API endpoints
full doc /v1/registry/pytorch-tokenizers
compatibility /v1/registry/pytorch-tokenizers/compatibility