Justine Tunney

OK so after investigating things, GNU libintl is GPL so we can't use it. I looked to FreeBSD for inspiration, and they don't do translation at all, at least not...

We should also begin writing a manual for Blinkenlights now that we have the GitHub website setup. The current website is https://justine.lol/blinkenlights/ which doesn't have a lot of information and...

> This hack still does not address the loader's problem though. And after reading your loader code for a while, I seem to understand what it does, step-by-step, but I...

> Note that I'm running master, the cygwin branch with JIT currently just crashes without a log for every binary (either crafted by me or obtained from the o//test folder)....

> Assuming nobody cares about windows it would be possible to allocate the giant buffer required for the model with shm_open to retain the loaded model in memory between executions....

Removing the help wanted tag because *it's here*. That doesn't mean you can't still participate in helping me do it!

> While great improvements in speed have been made recently, a virtualization layer simply can never be as efficient as native code is. This indicates a real misunderstanding of how...

Or just use POSIX and Cygwin / Mingw / Cosmo / etc. all have you covered.

Thank you for using llama.cpp and thank you for sharing your feature request. While you've provided valuable feedback on UX improvements, it overlaps a lot with what's being discussed in...

Thank you for sending us this change! This change would result in an 18% speedup of loading in the average case, however what @apage43 says is true. It doesn't make...