Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-17 08:19:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/release.yml
#	SECURITY.md
#	common/CMakeLists.txt
#	docs/speculative.md
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/set_rows.cl
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/test-export-graph-ops.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/rpc/CMakeLists.txt
#	tools/rpc/README.md
This commit is contained in:
Concedo
2026-06-29 16:43:44 +08:00
parent 0677ddd19d 277a105dc8
commit 3b867bd4b1
40 changed files with 1523 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+6 -1
View File
@@ -61,6 +61,7 @@
#include "models/deepseek2ocr.cpp"
#include "models/deepseek32.cpp"
#include "models/delta-net-base.cpp"
#include "models/dflash.cpp"
#include "models/dots1.cpp"
#include "models/dream.cpp"
#include "models/eagle3.cpp"
@@ -427,6 +428,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
return new llama_model_mistral3(params);
case LLM_ARCH_EAGLE3:
return new llama_model_eagle3(params);
case LLM_ARCH_DFLASH:
return new llama_model_dflash(params);
case LLM_ARCH_MIMO2:
return new llama_model_mimo2(params);
case LLM_ARCH_KIMI_LINEAR:
@@ -2630,6 +2633,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
case LLM_ARCH_STEP35:
case LLM_ARCH_TALKIE:
case LLM_ARCH_MELLUM:
case LLM_ARCH_DFLASH:
return LLAMA_ROPE_TYPE_NEOX;
case LLM_ARCH_QWEN2VL:
@@ -2753,7 +2757,8 @@ bool llama_model_has_encoder(const llama_model * model) {
switch (model->arch) {
case LLM_ARCH_T5:
case LLM_ARCH_T5ENCODER:
case LLM_ARCH_EAGLE3: return true;
case LLM_ARCH_EAGLE3:
case LLM_ARCH_DFLASH: return true;
default: return false;
}
}