vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-11 10:14:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use highs to solve the allocation program

Browse source
This commit is contained in:
Lizonghang 2025-01-15 10:04:04 +04:00
parent b577c10d25
commit 5d9aadf3d5
6 changed files with 614 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.h
View file

@ -158,7 +158,7 @@ struct gpt_params {
int32_t n_parallel = 1; // number of parallel sequences to decode
int32_t n_sequences = 1; // number of sequences to decode
float p_split = 0.1f; // speculative decoding split probability
int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default)
int32_t n_gpu_layers = 0; // number of layers to store in VRAM (0 - do not use by default)
int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-1 - use default)
int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors
float tensor_split[128] = {0}; // how split tensors should be distributed across GPUs