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 branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.pi/gg/SYSTEM.md
#	docs/speculative.md
#	ggml/src/ggml-virtgpu/virtgpu-shm.cpp
#	ggml/src/ggml-virtgpu/virtgpu.cpp
#	ggml/src/ggml-virtgpu/virtgpu.h
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/row_norm.wgsl
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-04 15:36:13 +08:00
parent 4a8a51a3a7 fa8feaed34
commit 2905c6254f
16 changed files with 384 additions and 283 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2 -2
View File
@@ -2109,7 +2109,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
}
}
if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, 0.0f)) {
if (ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, false)) {
// [TAG_DEEPSEEK2_YARN_LOG_MUL_FIX]
// cancel the factor from the convert script
hparams.rope_yarn_log_mul /= 0.1f;
@@ -2983,7 +2983,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_FAST, hparams.yarn_beta_fast, false);
ml.get_key(LLM_KV_ROPE_SCALING_YARN_BETA_SLOW, hparams.yarn_beta_slow, false);
ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, 0.0f);
ml.get_key(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul, false);
hparams.f_attn_temp_offset = 0.0f;