danlg

It would be great to be able to export the optimised / trained /selected model with ONNX so that the inference can be run fast on any cloud provider at...

Type: Improvement performance Issue: Most of the CPUs / Hardware are today multi core. 4 cores are common, some have 8 cores. The [DirectoryLoader](https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/directory_loader.html) is using a single core and...

macOS support for flutter-sound-stream

1

Hi, I understand macOS is not supported for flutter-sound-stream. Now that desktop (MacOS/darwin, windows) are supported by flutter, do you know the effort and high level specific code to support...

Hi, I understand Windows OS is not supported for flutter-sound-stream. Now that desktop (MacOS/darwin, windows) are supported by flutter, do you know the effort and high level specific code to...

LLM support, attention head and transformer architecture support for hls4ml

1

The **transformer** architecture (https://arxiv.org/pdf/1706.03762) has been instrumental to scale sequence neural networks. The transformer architecture is the fundamental building block of all LLMs. The trend of open sourcing LLM or...