diff options
author | saood06 <saood05@gmail.com> | 2025-05-28 00:18:25 -0500 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-05-28 08:18:25 +0300 |
commit | ccd6d9cdf6851f7042c48d682daf47bc0e2eca27 (patch) | |
tree | ac8324411fd50d18ef9eef08f75e18dd69d6299a /examples/server/server.cpp | |
parent | 09764678456f8991f6095118f3727d9d0b17b8c8 (diff) |
set cache_prompt default to true (#465)
Diffstat (limited to 'examples/server/server.cpp')
-rw-r--r-- | examples/server/server.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 360f571e..466bb339 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -112,7 +112,7 @@ struct server_task_multi { struct slot_params { bool stream = true; - bool cache_prompt = false; // remember the prompt to avoid reprocessing all prompt + bool cache_prompt = true; // remember the prompt to avoid reprocessing all prompt int32_t n_keep = 0; // number of tokens to keep from initial prompt int32_t n_discard = 0; // number of tokens after n_keep that may be discarded when shifting context, 0 defaults to half @@ -905,7 +905,7 @@ struct server_context { } slot.params.stream = json_value(data, "stream", false); - slot.params.cache_prompt = json_value(data, "cache_prompt", false); + slot.params.cache_prompt = json_value(data, "cache_prompt", true); slot.params.n_predict = json_value(data, "n_predict", json_value(data, "max_tokens", default_params.n_predict)); slot.sparams.top_k = json_value(data, "top_k", default_sparams.top_k); slot.sparams.top_p = json_value(data, "top_p", default_sparams.top_p); |