GitHub
BERT, Tokenizer, Python, WordPiece, pybind11,C++,Flash,Trie
What it does
🚀 **FlashTokenizer: World's Fastest CPU Tokenizer!** ⚡ 8~15x faster than `BertTokenizerFast` 🛠️ High-performance C++ 🔄 Parallel with OpenMP 📦 Easy pip install 💻 Cross-platform (Win/Mac/Linux) ▶️ Demo: https://youtu.be/a_sTiAXeSE0
Does a similar job
all alternatives →- TATokenDagger – A tokenizer faster than OpenAI's Tiktoken2025 · github.com · ▲281
TokenDagger is a drop-in replacement for OpenAI’s Tiktoken (the tokenizer behind Llama 3, Mistral, GPT-3.*, etc.). It’s written in C++ 17 with thin Python bindings, keeps the exact same BPE vocab/special-token rules, and focuses on raw speed. I’m teaching myself LLM internals by re-implementing the stack from first principles. Profiling TikToken’s Python/Rust implementation showed a lot of time was spent doing regex matching. Most of my perf gains come from a) using a faster jit-compiled regex engine; and b) simplifying the algorithm to forego regex matching special tokens at all.…
- F1FlashTokenizer – 10x faster C++ tokenizer for Python2025 · github.com · ▲5
I built a tokenizer in C++ with a Python binding that outperforms HuggingFace tokenizers by 10x on large inputs. It's optimized for minimal memory usage and latency. Benchmarks and comparison included in README. Would love feedback or contributions!
Gemini 3.1 Flash-LiteMar 2026 · blog.google · ▲311Best-in-class intelligence for your high-volume workloads
- WDWinkNLP delivers 600k tokens/second speed on browsers (MBP M1)2022 · github.com · ▲79
- MPMaple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhoneAug 2026 · deepgrove.ai · ▲173
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 28d ago · cactuscompute.com
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
