vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 09:04:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	Makefile
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/llava/MobileVLM-README.md
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/quantize/CMakeLists.txt
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-09-13 16:17:24 +08:00
commit e44ddf26ef
47 changed files with 117978 additions and 117646 deletions
Download patch file Download diff file Expand all files Collapse all files

4
gpttype_adapter.cpp
View file

@ -2388,7 +2388,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs)
if(debugmode==1 && file_format == FileFormat::GGUF_GENERIC)
{
llama_perf_reset(llama_ctx_v4, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_reset(llama_ctx_v4);
}
generation_finished = false; // Set current generation status
@ -3317,7 +3317,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs)
if(debugmode==1 && file_format == FileFormat::GGUF_GENERIC)
{
printf("\n");
llama_perf_print(llama_ctx_v4, LLAMA_PERF_TYPE_CONTEXT);
llama_perf_context_print(llama_ctx_v4);
}
time2 = timer_check();