vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-25 08:14:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	docs/backend/SYCL.md
#	ggml/src/ggml-cpu/ggml-cpu.c
#	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/gemv_moe_mxfp4_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemv_moe_q4_k_f32_ns.cl
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-gguf.cpp
#	tests/test-save-load-state.cpp
This commit is contained in:
Concedo 2026-07-13 20:53:37 +08:00
commit fa21872f97
76 changed files with 1399 additions and 1110 deletions
Download patch file Download diff file Expand all files Collapse all files

3
src/llama-model.cpp
View file

@ -451,8 +451,7 @@ llama_model * llama_model_create(llm_arch arch, const llama_model_params & param
if (model != nullptr) {
model->arch = arch;
auto & devices = model->devices;
if (!devices.empty() && devices[0].is_meta && !llm_arch_supports_sm_tensor(arch)) {
if (params.split_mode == LLAMA_SPLIT_MODE_TENSOR && !llm_arch_supports_sm_tensor(arch)) {
throw std::runtime_error(std::string("LLAMA_SPLIT_MODE_TENSOR not implemented for architecture '") + llm_arch_name(arch) + "'");
}
}