thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

common : restore grammar-based rejection sampling (#18137)

Browse source 
* common : restart grammar-based rejection sampling

* sampling : allow null samplers
This commit is contained in:
Georgi Gerganov 2025-12-17 19:46:00 +02:00 • committed by GitHub
parent a2c199e479
commit 4301e27319
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 76 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/speculative/speculative.cpp
View file

@ -242,7 +242,7 @@ int main(int argc, char ** argv) {
bool accept = false;
if (params.sampling.temp > 0) {
// stochastic verification
common_sampler_sample(smpl, ctx_tgt, drafts[s_keep].i_batch_tgt[i_dft]);
common_sampler_sample(smpl, ctx_tgt, drafts[s_keep].i_batch_tgt[i_dft], true);
auto & dist_tgt = *common_sampler_get_candidates(smpl, true);
@ -491,7 +491,7 @@ int main(int argc, char ** argv) {
continue;
}
common_sampler_sample(drafts[s].smpl, ctx_dft, drafts[s].i_batch_dft);
common_sampler_sample(drafts[s].smpl, ctx_dft, drafts[s].i_batch_dft, true);
const auto * cur_p = common_sampler_get_candidates(drafts[s].smpl, true);