vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	tests/test-grad0.cpp
#	tests/test-quantize-perf.cpp
This commit is contained in:
Concedo 2023-12-13 14:49:03 +08:00
commit c2c238b4f3
20 changed files with 44 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.h
View file

@ -216,7 +216,7 @@ extern "C" {
// Keep the booleans together to avoid misalignment during copy-by-value.
bool mul_mat_q; // if true, use experimental mul_mat_q kernels (DEPRECATED - always true)
bool logits_all; // the llama_eval() call computes all logits, not just the last one
bool logits_all; // the llama_eval() call computes all logits, not just the last one (DEPRECATED - set llama_batch.logits instead)
bool embedding; // embedding mode only
bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
};