ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

server : re-enable SWA speculative decoding (#14131)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-06-12 11:51:38 +03:00 • committed by GitHub
parent f6e1a7aa87
commit 7d516443dd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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;