vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-13 15:39:11 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/server.yml
#	CMakeLists.txt
#	cmake/common.cmake
#	ggml/src/ggml-virtgpu/apir_cs_ggml-rpc-front.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-backend.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-buffer-type.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-buffer.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-device.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.gen.h
#	ggml/src/ggml-virtgpu/backend/backend-dispatched.h
#	ggml/src/ggml-virtgpu/backend/backend.cpp
#	ggml/src/ggml-virtgpu/backend/shared/apir_cs.h
#	ggml/src/ggml-virtgpu/backend/shared/apir_cs_ggml.h
#	ggml/src/ggml-virtgpu/ggml-backend-buffer-type.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-device.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-reg.cpp
#	ggml/src/ggml-virtgpu/ggml-remoting.h
#	ggml/src/ggml-virtgpu/ggmlremoting_functions.yaml
#	ggml/src/ggml-virtgpu/regenerate_remoting.py
#	ggml/src/ggml-virtgpu/virtgpu-forward-backend.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-buffer-type.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-buffer.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-impl.h
#	ggml/src/ggml-virtgpu/virtgpu-forward.gen.h
#	ggml/src/ggml-virtgpu/virtgpu-shm.cpp
#	ggml/src/ggml-virtgpu/virtgpu.cpp
#	ggml/src/ggml-virtgpu/virtgpu.h
This commit is contained in:
Concedo 2026-02-04 16:21:06 +08:00
commit 1f803ae27b
22 changed files with 561 additions and 316 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama-context.cpp
View file

@ -1037,11 +1037,7 @@ bool llama_context::set_sampler(llama_seq_id seq_id, llama_sampler * sampler) {
llama_sampler_chain_n(sampler) > 0;
if (sampler && can_offload) {
ggml_backend_buffer_type_t buft = ggml_backend_dev_buffer_type(model.dev_output());
auto * host_buft = ggml_backend_dev_host_buffer_type(model.dev_output());
if (host_buft) {
buft = host_buft;
}
auto * buft = ggml_backend_dev_buffer_type(model.dev_output());
sampler->iface->backend_init(sampler, buft);