Piotr Wilkin (ilintar)
Piotr Wilkin (ilintar)
@gabe-l-hart guess you'll be interested in this one as well :)
@slaren @ggerganov Should be ready for final review.
@ggerganov Aight, paralellized CUMSUM, added docs, removed TRI_KEEP, renamed TRI_KEEP to TRI, added CONST with const1234d helpers.
Aight, @ggerganov @slaren @CISC it's ready to merge I think.
> As a constructive feedback for the future, try to split the changes in ggml in even smaller parts. It would improve the review process because there are many little...
Yes! This is exactly what I was thinking about :) can you give me push writes to your repo so I can contribute without doing PRs to PRs?
Aight, let me bounce my original idea - what if we just created a GBNF parser builder and used that to parse the messages? Then we have both problems (tool...
@aldehir Nah, you're probably right. I looked at the GBNF code and in fact it would take too much effort to extract the parsed content from there. We're better off...
Aight, I'm done with the hybrid ops and convert_hf_to_gguf refactoring cleanup, so I'll probably finally look at this tomorrow :>
@aldehir I thought it wouldn't make much sense for me to interfere in the key parser parts, so I went for the tests instead. I made a test case structure...