Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '1c3c9674de4d455f1e571bed808252af54932767' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/release.yml
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	examples/gen-docs/gen-docs.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/concat.cpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/fattn.cpp
#	models/templates/deepseek-ai-DeepSeek-V4.jinja
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	src/CMakeLists.txt
#	src/llama-model-loader.cpp
#	tests/CMakeLists.txt
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-chat.cpp
#	tests/test-sampling.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-08-07 18:16:11 +08:00
parent 7098c9c53f 1c3c9674de
commit 2580b4591d
51 changed files with 2686 additions and 780 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+4 -3
View File
@@ -1427,10 +1427,11 @@ 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)
float penalty_repeat, // 1.0 = disabled
float penalty_freq, // 0.0 = disabled
float penalty_present); // 0.0 = disabled
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
/// @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(