ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-06 22:40:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adaptive p: bugfix + optimization + refactor (#1155)

Browse Source 
* adaptive-p sampler: fix zeroed orig_probs bug and refactor

- Fix bug where original probabilities were captured as zero by calculating
  them from logits in llama_prep_adaptive_p (new).
- Replace vector with unordered_map to track candidate probabilities,
  filtering for relevance via logit delta (16.6f).
- Standardize API naming: llama_<action/verb>_<focus/name/topic>_<extra/info>
- Update function signatures to follow most other samplers.

* resolve merge bug

* adaptive-p: revert reordering function definitions
This commit is contained in:
dungquixote42
2026-01-18 01:26:06 -05:00
committed by GitHub
parent d71a3ec315
commit 6dfbef27ec
5 changed files with 121 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/llama.cpp
View File

@@ -7689,11 +7689,18 @@ void llama_sample_dry([[maybe_unused]] struct llama_context* ctx, struct llama_s
void llama_sample_adaptive_p(
[[maybe_unused]] struct llama_context * ctx,
struct llama_sampler_adaptive_p * adapt_p_ctx,
llama_token_data_array * candidates) {
llama_sampler_adaptive_p_apply(adapt_p_ctx, candidates);
llama_token_data_array * candidates,
struct llama_sampler_adaptive_p * adapt_p_ctx)
{
llama_sample_adaptive_p_impl(candidates, adapt_p_ctx);
}
void llama_prep_adaptive_p(llama_token_data_array * candidates, struct llama_sampler_adaptive_p * adapt_p_ctx)
{
llama_prep_adaptive_p_impl(candidates, adapt_p_ctx);
}
void llama_sample_repetition_penalties(
struct llama_context * ctx,
llama_token_data_array * candidates,
@@ -7736,10 +7743,9 @@ llama_token llama_sample_token(struct llama_context * ctx, llama_token_data_arra
llama_token llama_sample_token_adaptive_p(
struct llama_context * ctx,
llama_token_data_array * candidates,
struct llama_sampler_adaptive_p * adapt_p_ctx,
float * orig_probs)
struct llama_sampler_adaptive_p * adapt_p_ctx)
{
return llama_sample_token_adaptive_p_impl(&ctx->sampling, candidates, adapt_p_ctx, orig_probs);
return llama_sample_token_adaptive_p_impl(&ctx->sampling, candidates, adapt_p_ctx);
}
int llama_split_path(char * split_path, size_t maxlen, const char * path_prefix, int split_no, int split_count) {
@@ -7794,9 +7800,9 @@ void llama_sampler_dry_accept(struct llama_sampler_dry* smpl, llama_token token)
}
struct llama_sampler_adaptive_p * llama_sampler_init_adaptive_p(const float target, const float decay, const uint32_t seed)
struct llama_sampler_adaptive_p * llama_init_adaptive_p(const float target, const float decay, const uint32_t seed)
{
return llama_sampler_init_adaptive_p_impl(target, decay, seed);
return llama_init_adaptive_p_impl(target, decay, seed);
}