CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling : optimize samplers by reusing bucket sort (#15665)

Browse Source 
* sampling : optimize sorting using bucket sort in more places

ggml-ci

* sampling : do not sort in dist sampler

ggml-ci

* sampling : avoid heap allocations for sort buffers

ggml-ci

* common : add option to sort sampling candidates by probability

ggml-ci

* sampling : revert the change for preserving sort buffers

* sampling : use std::copy instead of memcpy

* sampling : clarify purpose of partial sort helpers

ggml-ci

* cont : remove wrong comment [no ci]

* common : update comment

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Georgi Gerganov
2025-08-31 20:41:02 +03:00
committed by GitHub
parent 0d161f021a
commit e92d53b29e
9 changed files with 227 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/llama.h
View File

@@ -206,7 +206,7 @@ extern "C" {
llama_token_data * data;
size_t size;
int64_t selected; // this is the index in the data array (i.e. not the token id)
bool sorted;
bool sorted; // note: do not assume the data is sorted - always check this flag
} llama_token_data_array;
typedef bool (*llama_progress_callback)(float progress, void * user_data);
@@ -1156,11 +1156,6 @@ extern "C" {
LLAMA_API struct llama_sampler * llama_sampler_init_greedy(void);
LLAMA_API struct llama_sampler * llama_sampler_init_dist (uint32_t seed);
/// @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
/// NOTE: Avoid using on the full vocabulary as the sorting can become slow. For example, apply top-k or top-p sampling first.
DEPRECATED(LLAMA_API struct llama_sampler * llama_sampler_init_softmax (void),
"will be removed in the future (see https://github.com/ggml-org/llama.cpp/pull/9896#discussion_r1800920915)");
/// @details Top-K sampling described in academic paper "The Curious Case of Neural Text Degeneration" https://arxiv.org/abs/1904.09751
/// Setting k <= 0 makes this a noop
LLAMA_API struct llama_sampler * llama_sampler_init_top_k (int32_t k);