CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix draft context not being released (#11354)

Browse Source
This commit is contained in:
Diego Devesa
2025-01-22 17:44:40 +01:00
committed by GitHub
parent c64d2becb1
commit 12c2bdf2de
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/server/server.cpp
View File

@@ -1772,6 +1772,9 @@ struct server_context {
// force F16 KV cache for the draft model for extra performance // force F16 KV cache for the draft model for extra performance
cparams_dft.type_k = GGML_TYPE_F16; cparams_dft.type_k = GGML_TYPE_F16;
cparams_dft.type_v = GGML_TYPE_F16; cparams_dft.type_v = GGML_TYPE_F16;
// the context is not needed - we will create one for each slot
llama_init_dft.context.reset();
} }
chat_templates = common_chat_templates_from_model(model, params_base.chat_template); chat_templates = common_chat_templates_from_model(model, params_base.chat_template);