grammars: 1.5x faster inference w/ complex grammars (vector reserves / reuses)#6609

Merged

ochafik merged 6 commits intoggml-org:masterfrom

ochafik:grammar-speedup3

Apr 11, 2024

Commits on Apr 11, 2024

grammars: reserve rejects & next candidates
Olivier Chafik
committed
grammars: reuse new_stacks
Olivier Chafik
committed
grammars: fix missing sig change in llama.h
Olivier Chafik
committed
grammars: fix test (api changed)
Olivier Chafik
committed
grammars: update gbnf-validator.cpp
Olivier Chafik
committed
grammars: simpler syntax (no swap)
Olivier Chafik
committed