vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-20 01:09:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '2cd20b72ed' into concedo_experimental

Browse source 
# Conflicts:
#	CONTRIBUTING.md
#	docs/backend/CANN.md
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/README.md
#	docs/backend/snapdragon/windows.md
#	docs/build.md
#	docs/multimodal/MobileVLM.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	examples/debug/README.md
#	examples/llama.vim
#	examples/model-conversion/README.md
#	examples/sycl/README.md
#	ggml/src/ggml-cpu/amx/mmq.cpp
#	ggml/src/ggml-cpu/arch/x86/repack.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-copy.h
#	ggml/src/ggml-hexagon/htp/hvx-inverse.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/worker-pool.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/quants.hpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/pr2wt.sh
#	scripts/server-bench.py
#	scripts/snapdragon/windows/run-cli.ps1
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/completion/README.md
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/README.md
#	tools/perplexity/README.md
#	tools/server/public_simplechat/readme.md
#	tools/server/tests/README.md
This commit is contained in:
Concedo 2026-03-10 22:11:08 +08:00
commit 746664fde6
107 changed files with 1037 additions and 314 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama-context.cpp
View file

@ -161,7 +161,7 @@ llama_context::llama_context(
cparams.op_offload = params.op_offload;
cparams.kv_unified = params.kv_unified;
// intialized later
// initialized later
cparams.pipeline_parallel = false;
{
@ -1991,7 +1991,7 @@ ggml_cgraph * llama_context::graph_reserve(
ggml_backend_sched_reset(sched.get());
// when the scheduler is reset, we cannnot reuse the old graph, so we reset the previous graph result to prevent that
// when the scheduler is reset, we cannot reuse the old graph, so we reset the previous graph result to prevent that
gf_res_prev->reset();
// store the n_outputs as it is, and restore it afterwards