tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 04:45:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

speculative : update default params

Browse Source
This commit is contained in:
Georgi Gerganov
2025-02-19 08:20:10 +02:00
parent 9626d9351a
commit 965ad1c08a
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/speculative.h
View File

@ -9,7 +9,7 @@ struct common_speculative_params {
int n_draft = 16; // max drafted tokens
int n_reuse = 256;
float p_min = 0.9f; // min probability required to accept a token in the draft
float p_min = 0.75f; // min probability required to accept a token in the draft
};
struct common_speculative * common_speculative_init(struct llama_context * ctx_dft);