CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : reuse compute graphs

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-01 15:59:43 +03:00
parent bac8bed248
commit 76681e3c73
17 changed files with 458 additions and 187 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.cpp
View File

@@ -1157,6 +1157,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
cparams.no_perf = params.no_perf;
cparams.op_offload = !params.no_op_offload;
cparams.swa_full = params.swa_full;
cparams.graph_reuse = params.graph_reuse;
cparams.type_k = params.cache_type_k;
cparams.type_v = params.cache_type_v;