← 최신 프로덕트

FlashTokenizer

10x faster C++ tokenizer for Python. EFFICIENT AND OPTIMIZED TOKENIZER ENGINE FOR LLM INFERENCE SERVING. I built a tokenizer in C++ with a Python binding that outperforms HuggingFace tokenizers by 10x on large inputs.

오픈소스

457 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Rust BPE tokenizer for Qwen models that's 12x faster than HuggingFace

    github.com

    A blazing-fast BPE tokenizer for Qwen models built with Rust

    Hacker News5점

  2. Achilles

    github.com

    Automatic profiling and C++ optimization of Python via LLMs

    Hacker News7점

  3. Tiny-vLLM

    github.com

    high performance LLM inference engine in C++ and CUDA

    Hacker News205점

  4. Tokensift

    github.com

    an open-sourced token-efficiency linter for LLM prompts

    Hacker News6점

  5. TokenDagger

    github.com

    A tokenizer faster than OpenAI's Tiktoken

    Hacker News281점