Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	SECURITY.md
#	build-xcframework.sh
#	ci/run.sh
#	docs/development/HOWTO-add-model.md
#	examples/model-conversion/scripts/causal/convert-model.sh
#	examples/model-conversion/scripts/embedding/convert-model.sh
#	scripts/sync_vendor.py
#	scripts/ui-assets.cmake
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-grammar-parser.cpp
#	tests/test-llama-archs.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/mtmd.h
#	tools/mtmd/tests/test-deepseek-ocr.py
#	tools/server/README.md
#	tools/tts/CMakeLists.txt
#	tools/tts/convert_pt_to_hf.py
This commit is contained in:
Concedo
2026-08-07 20:46:56 +08:00
parent 56368c0fd4 6a32c29a74
commit 8a16f96307
125 changed files with 7633 additions and 2869 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+2 -3
View File
@@ -1428,7 +1428,7 @@ extern "C" {
/// NOTE: Avoid using on the full vocabulary as searching for repeated tokens can become slow. For example, apply top-k or top-p sampling first.
LLAMA_API struct llama_sampler * llama_sampler_init_penalties(
int32_t n_vocab,
int32_t penalty_last_n, // last n tokens to penalize (0 = disable penalty, -1 = context size)
int32_t penalty_last_n, // last n tokens to penalize (0 = disable penalty)
float penalty_repeat, // must be > 0.0, 1.0 = disabled
float penalty_freq, // must be finite, 0.0 = disabled
float penalty_present); // must be finite, 0.0 = disabled
@@ -1436,11 +1436,10 @@ extern "C" {
/// @details DRY sampler, designed by p-e-w, as described in: https://github.com/oobabooga/text-generation-webui/pull/5677, porting Koboldcpp implementation authored by pi6am: https://github.com/LostRuins/koboldcpp/pull/982
LLAMA_API struct llama_sampler * llama_sampler_init_dry(
const struct llama_vocab * vocab,
int32_t n_ctx_train,
float dry_multiplier,
float dry_base,
int32_t dry_allowed_length,
int32_t dry_penalty_last_n,
int32_t dry_penalty_last_n, // last n tokens to penalize (0 = disable penalty)
const char ** seq_breakers,
size_t num_breakers);