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 : added --no-prefill-assistant flag (#13608)

Browse Source 
* added no-prefill-assistant flag

* reworded documentation comment

* updated server README.md
This commit is contained in:
Isaac McFadyen
2025-05-17 17:59:48 -04:00
committed by GitHub
parent e3a7cf6c5b
commit 6a2bc8bfb7
5 changed files with 17 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
common/arg.cpp
View File

@ -2880,6 +2880,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.chat_template = read_file(value);
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CHAT_TEMPLATE_FILE"));
add_opt(common_arg(
{"--no-prefill-assistant"},
string_format(
"whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)\n"
"when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled\n"
),
[](common_params & params) {
params.prefill_assistant = false;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_PREFILL_ASSISTANT"));
add_opt(common_arg(
{"-sps", "--slot-prompt-similarity"}, "SIMILARITY",
string_format("how much the prompt of a request must match the prompt of a slot in order to use that slot (default: %.2f, 0.0 = disabled)\n", params.slot_prompt_similarity),