nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 18 Packages Projects Releases Wiki Activity

spec : refactor params (#22397)

Browse Source 
* spec : refactor params

* cont : fix

* cont : rename "sparam" to "sampling"

* cont : add spec params category

* cont : add info about removed arguments

* cont : skip param length check for spec params

* cont : adapt server tests
This commit is contained in:
Georgi Gerganov
2026-04-28 09:07:33 +03:00
committed by GitHub
parent 516e8d7a8a
commit 14e733e36f
18 changed files with 661 additions and 409 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/speculative.h
+3
View File
@@ -33,6 +33,9 @@ llama_tokens common_speculative_draft(
// informs the speculative decoder that n_accepted tokens were accepted by the target model
void common_speculative_accept(common_speculative * spec, uint16_t n_accepted);
int32_t common_speculative_n_max(const common_speculative * spec, const common_params_speculative & params);
int32_t common_speculative_n_min(const common_speculative * spec, const common_params_speculative & params);
// print statistics about the speculative decoding
void common_speculative_print_stats(const common_speculative * spec);