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

correct comment placement

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-12-19 12:02:11 +01:00
parent 65ef1c8dc9
commit a217382b25
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -1958,7 +1958,6 @@ struct server_context {
size_t n_probs = slot.params.sampling.n_probs; size_t n_probs = slot.params.sampling.n_probs;
int n_vocab = llama_n_vocab(llama_get_model(ctx)); int n_vocab = llama_n_vocab(llama_get_model(ctx));
if (post_sampling) { if (post_sampling) {
// TODO: optimize this with min-p optimization
const auto * cur_p = common_sampler_get_candidates(slot.smpl); const auto * cur_p = common_sampler_get_candidates(slot.smpl);
const size_t max_probs = cur_p->size; const size_t max_probs = cur_p->size;
@ -1982,6 +1981,7 @@ struct server_context {
} }
} }
} else { } else {
// TODO: optimize this with min-p optimization
std::vector<llama_token_data> cur = get_token_probabilities(ctx, idx); std::vector<llama_token_data> cur = get_token_probabilities(ctx, idx);
bool found_sampled_tok = false; bool found_sampled_tok = false;