TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
- llama-cpp
- pipeline-parallelism
- prefill-decode
- rtx-3060
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
A ChatGPT-based tool to decode Jupyter notebooks and the similar python notebook environments like Google Colab, etc.
Lightweight PHP library for encoding/decoding TOON (Token-Oriented Object Notation). A human-readable, LLM-friendly alternative to JSON.
- decoder
- encoder
- json
- llm