vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

added new flags --moeexperts --failsafe --draftgpulayers and --draftgpuid

Browse source
This commit is contained in:
Concedo 2024-12-13 17:11:59 +08:00
parent bcec998979
commit 595cc6975f
4 changed files with 56 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp
View file

@ -4142,8 +4142,8 @@ template <typename BLOC_TYPE, int64_t INTER_SIZE, int64_t NB_COLS> class tensor_
}
int repack(struct ggml_tensor * t, const void * data, size_t data_size) override {
GGML_LOG_DEBUG("%s: repack tensor %s with %s_%dx%d\n", __func__, t->name, ggml_type_name(t->type),
(int) NB_COLS, (int) INTER_SIZE);
// GGML_LOG_DEBUG("%s: repack tensor %s with %s_%dx%d\n", __func__, t->name, ggml_type_name(t->type),
// (int) NB_COLS, (int) INTER_SIZE);
return ggml::cpu::aarch64::repack<BLOC_TYPE, INTER_SIZE, NB_COLS>(t, data, data_size);
}
};
@ -4164,7 +4164,7 @@ static void flag_aarch_prepacked_quant(int type)
{
if(!kcpp_q_already_repacked)
{
printf("\nWARNING! Legacy aarch64 prepacked QM_0_M_N quant (%d) detected! Please switch to Q4_0!\n",type);
printf("\nWARNING! Legacy aarch64 prepacked Q4_0_M_N quant (%d) detected! Please switch to Q4_0!\n",type);
kcpp_q_already_repacked = true;
}
}