mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-04-28 11:40:43 +00:00
fit-params : refactor + add option to output estimated memory per device (#22171)
* fit-params : add option to output estimated memory per device * cont : minor * cont : refactor * cont : move fit params implementation to libcommon * cont : header * cont : headers * cont : codeowners
This commit is contained in:
parent
ff6b1062af
commit
cfe9838d26
19 changed files with 1123 additions and 980 deletions
|
|
@ -1,10 +1,12 @@
|
|||
#include "sampling.h"
|
||||
|
||||
#include "common.h"
|
||||
#include "ggml.h"
|
||||
#include "fit.h"
|
||||
#include "log.h"
|
||||
#include "reasoning-budget.h"
|
||||
|
||||
#include "ggml.h"
|
||||
|
||||
#include <algorithm>
|
||||
#include <cctype>
|
||||
#include <climits>
|
||||
|
|
@ -511,7 +513,7 @@ void common_perf_print(const struct llama_context * ctx, const struct common_sam
|
|||
LOG_INF("%s: unaccounted time = %10.2f ms / %5.1f %% (total - sampling - prompt eval - eval) / (total)\n", __func__, t_unacc_ms, t_unacc_pc);
|
||||
LOG_INF("%s: graphs reused = %10d\n", __func__, data.n_reused);
|
||||
|
||||
llama_memory_breakdown_print(ctx);
|
||||
common_memory_breakdown_print(ctx);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue