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

parallel : add option for non-shared and larger prompts (#13598)

Browse Source 
* parallel : add option for non-shared and larger prompts

* parallel : update readme [no ci]

* cont : add note about base models [no ci]

* parallel : better var name

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-17 12:58:55 +03:00
committed by GitHub
parent 2f5a4e1e09
commit 518329b2d4
3 changed files with 99 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/arg.cpp
View File

@ -2585,7 +2585,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, int value) {
params.n_junk = value;
}
).set_examples({LLAMA_EXAMPLE_PASSKEY}));
).set_examples({LLAMA_EXAMPLE_PASSKEY, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"--pos"}, "N",
string_format("position of the passkey in the junk text (default: %d)", params.i_pos),
@ -2648,7 +2648,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.is_pp_shared = true;
}
).set_examples({LLAMA_EXAMPLE_BENCH}));
).set_examples({LLAMA_EXAMPLE_BENCH, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"-npp"}, "n0,n1,...",
"number of prompt tokens",