all AI news
How fast is JS tiktoken?
Dec. 18, 2023, 11:06 a.m. | Maxim Saplin
DEV Community dev.to
IMO, it is very fast, considering the performance against the OpenAI's Rust implementation (wrapped into a Python package). Both pure JS and Web Assembly (WASM) ports have decent speed, even interpreted JS version is within 10% margin on small and medium texts.
Below you can find execution times for text to tokens encoding (smaller is better).
- Small text (68 tokens)
Python/Rust (tiktoken 0.5.2) ████ (0.04ms)
Pure JS (js-tiktoken 1.0.8) █████ (0.05ms)
JS/WASM (tiktoken 1.0.11) ██████████ (0.11ms)
@dqbd/WASM 1.0.7 ██████████████████ (0.18ms) …
ai assembly encoding implementation interpreted javascript llm machinelearning medium openai package performance python rust small speed text tokens wasm web web assembly
More from dev.to / DEV Community
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote