CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix speculative decoding build on windows (#5874)

Browse Source
This commit is contained in:
Jeffrey Quesnelle
2024-03-04 19:23:06 -08:00
committed by GitHub
parent 1d41d6f7c2
commit 29eee40474
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/speculative/speculative.cpp
View File

@@ -226,7 +226,7 @@ int main(int argc, char ** argv) {
while (active_seqs.size() > 0) { while (active_seqs.size() > 0) {
// randomly select a sequence to verify from active sequences // randomly select a sequence to verify from active sequences
std::uniform_int_distribution<u_int> u_int_dist(0, active_seqs.size() - 1); std::uniform_int_distribution<unsigned int> u_int_dist(0, active_seqs.size() - 1);
int s = *std::next(active_seqs.begin(), u_int_dist(rng)); int s = *std::next(active_seqs.begin(), u_int_dist(rng));
if (i_dft >= (int) drafts[s].tokens.size()) { if (i_dft >= (int) drafts[s].tokens.size()) {
drafts[s].active = false; drafts[s].active = false;