vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-07 17:22:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	common/common.cpp
#	examples/batched/README.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/arch-fallback.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/sync-ggml.last
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo 2025-11-25 16:38:07 +08:00
commit 724763fdec
55 changed files with 5248 additions and 3753 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-context.cpp
View file

@ -1250,7 +1250,7 @@ int llama_context::decode(const llama_batch & batch_inp) {
// make the outputs have the same order they had in the user-provided batch
// note: this is mostly relevant for recurrent models atm
if (!sorted_output) {
if (!sorted_output && n_outputs > 1) {
GGML_ASSERT((size_t) n_outputs == out_ids.size());
// TODO: is there something more efficient which also minimizes swaps?