vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-20 17:54:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/ai-issues.yml
#	CONTRIBUTING.md
#	docs/autoparser.md
#	docs/ops.md
#	docs/ops/Metal.csv
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp_iface.idl
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hip/CMakeLists.txt
#	models/templates/Apriel-1.6-15b-Thinker-fixed.jinja
#	models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja
#	models/templates/deepseek-ai-DeepSeek-V3.1.jinja
#	models/templates/llama-cpp-deepseek-r1.jinja
#	models/templates/meetkai-functionary-medium-v3.1.jinja
#	scripts/fetch_server_test_models.py
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-mtmd.sh
#	scripts/snapdragon/adb/run-tool.sh
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2026-03-21 12:06:01 +08:00
commit 6054bacadd
33 changed files with 834 additions and 491 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-context.cpp
View file

@ -1948,6 +1948,7 @@ uint32_t llama_context::output_reserve(int32_t n_outputs) {
LLAMA_LOG_ERROR("%s: failed to allocate output buffer of size %.2f MiB\n", __func__, new_size / (1024.0 * 1024.0));
return 0;
}
ggml_backend_buffer_clear(buf_output.get(), 0);
}
float * output_base = (float *) ggml_backend_buffer_get_base(buf_output.get());