doing something
Added two runtimes for this model #rust
onnxruntime uses ort library, it's very useful and convenient
i've added cuda provider and it works without issues
on macos i had a problem with coreml linking
i've added cuda provider and it works without issues
on macos i had a problem with coreml linking
doing something
onnxruntime uses ort library, it's very useful and convenient i've added cuda provider and it works without issues on macos i had a problem with coreml linking
candle supports accelerate inside, so we can speed up execution with it
doing something
https://arrow.apache.org/rust/parquet_rewrite/index.html Useful tool to optimize files #optimization
Made a colab to learn how to use parquet_rewrite
Link: https://colab.research.google.com/drive/1fgEJyt4dcUNuGzlfVe_aNmegllcIZJY9?usp=sharing
#rust #data
Link: https://colab.research.google.com/drive/1fgEJyt4dcUNuGzlfVe_aNmegllcIZJY9?usp=sharing
#rust #data
vLLM now supports Gemma 3, so I've made a colab to show how one can use it
Link: https://colab.research.google.com/drive/1R3yY3XLcxXGbHiBs3s1CEGeSTJLkXMuZ?usp=sharing
#llm #ai #cv
Link: https://colab.research.google.com/drive/1R3yY3XLcxXGbHiBs3s1CEGeSTJLkXMuZ?usp=sharing
#llm #ai #cv