diff options
author | Georgi Gerganov <ggerganov@gmail.com> | 2023-07-21 13:10:51 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2023-07-21 13:10:51 +0300 |
commit | ae178ab46bfd6ecb2422da5dad441a4e2fef8b7e (patch) | |
tree | 064a13d048ecd596bbd57bd081c9615aa91ebbf6 /llama.h | |
parent | 54e3bc76fed914f8d4a30a7a50c19867cccb1338 (diff) |
llama : make tensor_split ptr instead of array (#2272)
Diffstat (limited to 'llama.h')
-rw-r--r-- | llama.h | 3 |
1 files changed, 2 insertions, 1 deletions
@@ -88,7 +88,8 @@ extern "C" { int32_t n_batch; // prompt processing batch size int32_t n_gpu_layers; // number of layers to store in VRAM int32_t main_gpu; // the GPU that is used for scratch and small tensors - float tensor_split[LLAMA_MAX_DEVICES]; // how to split layers across multiple GPUs + + const float * tensor_split; // how to split layers across multiple GPUs (size: LLAMA_MAX_DEVICES) // ref: https://github.com/ggerganov/llama.cpp/pull/2054 float rope_freq_base; // RoPE base frequency |