ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-02 01:50:01 +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

15
include/llama.h
View File

@@ -1384,16 +1384,20 @@ LLAMA_API struct llama_grammar* llama_sampler_init_grammar_lazy_patterns(
/// @details Adaptive p sampler initializer
/// @param target Select tokens near this probability (valid range 0.0 to 1.0; <0 = disabled)
/// @param decay Decay rate for target adaptation over time. lower values -> faster but less stable adaptation. (valid range 0.0 to 1.0; ≤0 = no adaptation)
LLAMA_API struct llama_sampler_adaptive_p * llama_sampler_init_adaptive_p(
LLAMA_API struct llama_sampler_adaptive_p * llama_init_adaptive_p(
const float target,
const float decay,
const uint32_t seed);
void llama_prep_adaptive_p(
llama_token_data_array * candidates,
struct llama_sampler_adaptive_p * adapt_p_ctx);
/// @details Adaptive p sampler described in https://github.com/MrJackSpade/adaptive-p-docs/blob/main/README.md
void llama_sample_adaptive_p(
struct llama_context * ctx,
struct llama_sampler_adaptive_p * adapt_p_ctx,
llama_token_data_array * candidates);
struct llama_context * ctx,
llama_token_data_array * candidates,
struct llama_sampler_adaptive_p * adapt_p_ctx);
/// @details Mirostat 1.0 algorithm described in the paper https://arxiv.org/abs/2007.14966. Uses tokens instead of words.
@@ -1437,8 +1441,7 @@ LLAMA_API struct llama_grammar* llama_sampler_init_grammar_lazy_patterns(
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);
//
// Model split