David Hinkle

Results 5 comments of David Hinkle

Would love to see the License issue fixed. It makes it a lot easier for those of us in the commercial space to engage.

I feel like this is very important, if they don't implement batch inferencing I can't really consider it over llama.cpp's GBNF grammers.

I'm not very strong on the theory, but llama.cpp does support continuous batch inference with a grammar file. It had grammar support and continuous batching support for a while, but...

I need to understand this as well if it is possible.