ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-06 03:50:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

save checkpoint during pp

Browse Source
This commit is contained in:
firecoperana
2026-02-25 19:05:54 -06:00
parent 233898704c
commit 7962e9a4b3
4 changed files with 47 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.cpp
View File

@@ -2247,7 +2247,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", "-cd, --ctx-size-draft N", "size of the prompt context for the draft model (default: %d, 0 = loaded from model)", params.speculative.n_ctx });
options.push_back({ "*", "--ctx-checkpoints N", "max number of context checkpoints to create per slot (default: %d)",params.ctx_checkpoints_n});
options.push_back({ "*", "--ctx-checkpoints-interval N", "number of tokens between each context checkpoint. (default: %d, <=0 disable)",params.ctx_checkpoints_interval});
options.push_back({ "*", "--ctx-checkpoints-interval N", "minimum number of tokens between each context checkpoint. (default: %d, <=0 disable)",params.ctx_checkpoints_interval});
options.push_back({ "*", "-cram, --cache-ram N", "set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)",params.cache_ram_mib });
options.push_back({ "*", "-crs, --cache-ram-similarity N", "max of similarity of prompt tokens to cache tokens that triggers prompt cache (default: %.2f).",params.cache_ram_similarity });
options.push_back({ "*", "-cram-n-min --cache-ram-n-min N", "minimum number of the cached tokens that triggers prompt cache (default: %d).", params.cache_ram_n_min });