tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : re-enable swa speculative decoding

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-11 20:22:06 +03:00
parent f6e1a7aa87
commit 36fce98281
1 changed files with 0 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tools/server/server.cpp
View File

@ -2017,11 +2017,6 @@ struct server_context {
params_base.n_cache_reuse = 0; params_base.n_cache_reuse = 0;
SRV_WRN("%s\n", "cache_reuse is not supported by this context, it will be disabled"); SRV_WRN("%s\n", "cache_reuse is not supported by this context, it will be disabled");
} }
if (!params_base.speculative.model.path.empty()) {
SRV_ERR("%s\n", "err: speculative decode is not supported by this context");
return false;
}
} }
return true; return true;