Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
-
Updated
Dec 3, 2024 - JavaScript
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
JavaScript bindings for the ggml-js library
Bring your own copilot server and customize commands to refactor instead of autofill or tabbed completion.
🤖 Build engaging AI chat experiences with Ultralytics LLM, a lightweight JavaScript client for web applications, delivered via jsDelivr with zero dependencies.
To associate your repository with the ggml topic, visit your repo's landing page and select "manage topics."