Post

~1000x faster than HuggingFace's tokenizers, drop-in replacement.

Note that both HF tokenizers and tiktoken are already running multithreaded Rust!

Gigatoken is the fastest tokenizer for language modeling. It supports a wide range of CPU hardware, and nearly all commonly used tokenizers. See the Benchmarks section for detailed throughput numbers across tokenizers and CPUs.

Gigatoken can be used with its own API, or in compatibility mode with HuggingFace Tokenizers or Tiktoken.

A substantial amount of effort has been put into making sure the outputs match exactly with what you would get with HuggingFace Tokenizers in this setting, but this is at a non-negligible cost to performance. You can still expect way faster performance across the board, but not quite the 1000x you will get with the Gigatoken API.

Using the Gigatoken API lets the Rust implementation read data directly, and skips as much overhead as possible while allowing for maximum parallelism. Keep in mind that passing Python data structures through this API still incurs the overhead of reading from Python.