Jan Wassenberg

Hi @malaterre , would you mind rebasing?

Thanks! I checked with ubsan and we get test failures because we were checking for alignment to the pointer type, not to the pointed-to type. Fixing by adding RemovePtr.

Rerunning CI now..

Hi @yukiarimo , I believe no special action is required for this code, if you are able to build code for WASM, you are also able to build this for...

Closing, please feel free to reopen if you'd like to discuss specifics :)

Hi @sanjay920 , a quick FYI on the implementation: `Compressor` in compression/compress-inl.h takes care of writing the SBS, so we've got that part covered. The missing bit is getting your...

I think this is now working, please feel free to reopen if you'd like to discuss or have an issue with the scripts.

Thanks for the suggestion, makes sense. Work is underway :)

FYI we do support an experimental 4.5 bit quantization method (NUQ), but those weights are not available on Kaggle. We can more easily support this once we are able to...

An update on this, we do have the ability to import from pytorch weights. Work is still ongoing on evaluating the nonuniform 4.5-bit format. I'm increasingly concerned about uniform integer...