Skip to content

sampling : make sure samplers return at least 1 token #13822

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 27, 2025
Merged

sampling : make sure samplers return at least 1 token #13822

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fe12a5d
sampling : min-p should always return at least one token
ggerganov May 27, 2025
76f31ab
sampling : same for typical sampling
ggerganov May 27, 2025
9065ca7
tests : sampling tests use min_keep == 0
ggerganov May 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/llama-sampling.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -798,7 +798,7 @@ static void llama_sampler_min_p_apply(struct llama_sampler * smpl, llama_token_d
}

// if we have enough values the operation was a success
if (filtered_tokens.size() >= ctx->min_keep) {
if (!filtered_tokens.empty() && filtered_tokens.size() >= ctx->min_keep) {
memcpy(cur_p->data, filtered_tokens.data(), filtered_tokens.size()*sizeof(llama_token_data));
cur_p->size = filtered_tokens.size();
min_p_applied = true;
Expand Down Expand Up @@ -909,7 +909,7 @@ static void llama_sampler_typical_apply(struct llama_sampler * smpl, llama_token
cum_sum += cur_p->data[idx].p;

// Check if the running sum is greater than typical or if we have kept at least min_keep tokens
if (cum_sum > ctx->p && i >= ctx->min_keep - 1) {
if (cum_sum > ctx->p && (ctx->min_keep == 0 || i >= ctx->min_keep - 1)) {
last_idx = i + 1;
break;
}
Expand Down
11 changes: 6 additions & 5 deletions tests/test-sampling.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ static void test_top_p(const std::vector<float> & probs, const std::vector<float
sampler_tester tester(probs, probs_expected);

DUMP(&tester.cur_p);
tester.apply(llama_sampler_init_top_p(p, 1));
tester.apply(llama_sampler_init_top_p(p, 0));
tester.apply(llama_sampler_init_dist (0));
DUMP(&tester.cur_p);

Expand All @@ -109,7 +109,7 @@ static void test_min_p(const std::vector<float> & probs, const std::vector<float
sampler_tester tester(probs, probs_expected);

DUMP(&tester.cur_p);
tester.apply(llama_sampler_init_min_p(p, 1));
tester.apply(llama_sampler_init_min_p(p, 0));
tester.apply(llama_sampler_init_dist (0));
DUMP(&tester.cur_p);

Expand All @@ -130,7 +130,7 @@ static void test_typical(const std::vector<float> & probs, const std::vector<flo
sampler_tester tester(probs, probs_expected);

DUMP(&tester.cur_p);
tester.apply(llama_sampler_init_typical(p, 1));
tester.apply(llama_sampler_init_typical(p, 0));
DUMP(&tester.cur_p);

tester.check();
Expand Down Expand Up @@ -332,6 +332,7 @@ int main(void) {
test_min_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f/0.7f, 0.3f/0.7f}, 0.74f);
test_min_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f/0.4f}, 0.76f);
test_min_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f/0.4f}, 1.00f);
test_min_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f/0.4f}, 1.05f);

printf("XTC should:\n");
test_xtc({0.4f, 0.3f, 0.2f, 0.1f}, {0.1f}, 0.99f, 0.09f);
Expand All @@ -341,8 +342,8 @@ int main(void) {
printf("XTC should not:\n");
test_xtc({0.4f, 0.3f, 0.2f, 0.1f}, {0.4f, 0.3f, 0.2f, 0.1f}, 0.99f, 0.39f);

test_typical({0.97f, 0.01f, 0.01f, 0.01f}, {0.97f}, 0.5f);
test_typical({0.4f, 0.2f, 0.2f, 0.2f}, {0.2f, 0.2f, 0.2f}, 0.5f);
test_typical({0.97f, 0.01f, 0.01f, 0.01f}, {0.97f}, 0.5f);
test_typical({0.4f, 0.2f, 0.2f, 0.2f}, {0.2f, 0.2f, 0.2f}, 0.5f);

test_penalties({0.2f, 0.2f, 0.2f, 0.2f, 0.2f}, {0}, {0.25f, 0.25f, 0.25f, 0.25f, 0}, 50.0f, 0.0f, 0.0f);
test_penalties({0.2f, 0.2f, 0.2f, 0.2f, 0.2f}, {0, 1, 2}, {0.5f, 0.5f, 0, 0, 0}, 50.0f, 0.0f, 0.0f);
Expand Down
Loading