ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

speculative : add grammar support (#2991)

Browse source 
* speculative : add grammar support

* grammars : add json_arr.gbnf

* grammar : add comments to new grammar file

* grammar : remove one nested level

* common : warm-up with 2 tokens - seems to work better

* speculative : print draft token pieces

* speculative : reuse grammar parser + better logs and comments

* speculative : avoid grammar_mem

* make : fix speculative build
This commit is contained in:
Georgi Gerganov 2023-09-05 08:46:17 +03:00 • committed by GitHub
parent 2ba85c8609
commit 921772104b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 126 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

19
llama.cpp
View file

@ -3850,6 +3850,25 @@ void llama_grammar_free(struct llama_grammar * grammar) {
delete grammar;
}
struct llama_grammar * llama_grammar_copy(const struct llama_grammar * grammar) {
llama_grammar * result = new llama_grammar{ grammar->rules, grammar->stacks, grammar->partial_utf8 };
// redirect elements in stacks to point to new rules
for (size_t is = 0; is < result->stacks.size(); is++) {
for (size_t ie = 0; ie < result->stacks[is].size(); ie++) {
for (size_t ir0 = 0; ir0 < grammar->rules.size(); ir0++) {
for (size_t ir1 = 0; ir1 < grammar->rules[ir0].size(); ir1++) {
if (grammar->stacks[is][ie] == &grammar->rules[ir0][ir1]) {
result->stacks[is][ie] = &result->rules[ir0][ir1];
}
}
}
}
}
return result;
}
//
// sampling
//