tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-15 04:33:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : enable -td and -tbd parameters (#15172)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-08-13 15:43:00 +02:00
committed by GitHub
parent c24f4e2688
commit b3e16665e1
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/server.cpp
View File

@@ -2015,6 +2015,8 @@ struct server_context {
params_dft.cache_type_k = params_base.speculative.cache_type_k;
params_dft.cache_type_v = params_base.speculative.cache_type_v;
params_dft.cpuparams.n_threads = params_base.speculative.cpuparams.n_threads;
params_dft.cpuparams_batch.n_threads = params_base.speculative.cpuparams_batch.n_threads;
params_dft.tensor_buft_overrides = params_base.speculative.tensor_buft_overrides;
llama_init_dft = common_init_from_params(params_dft);