tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-16 13:12:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : enable -td and -tbd parameters (#15172)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-08-13 15:43:00 +02:00
committed by GitHub
parent c24f4e2688
commit b3e16665e1
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
common/arg.cpp
View File

@@ -3163,7 +3163,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.cpuparams.n_threads = std::thread::hardware_concurrency();
}
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE}));
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"-tbd", "--threads-batch-draft"}, "N",
"number of threads to use during batch and prompt processing (default: same as --threads-draft)",
@@ -3173,7 +3173,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.cpuparams_batch.n_threads = std::thread::hardware_concurrency();
}
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE}));
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"-Cd", "--cpu-mask-draft"}, "M",
"Draft model CPU affinity mask. Complements cpu-range-draft (default: same as --cpu-mask)",