]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
common : more accurate sampling timing (#17382)
authorGeorgi Gerganov <redacted>
Thu, 20 Nov 2025 11:40:10 +0000 (13:40 +0200)
committerGitHub <redacted>
Thu, 20 Nov 2025 11:40:10 +0000 (13:40 +0200)
commit196f5083efe636ceaf247aa4dca5593c6c2b743f
tree536d01242201571770f33e9761d59eb480df0966
parent5088b435d47614b03d8e05d31f4dc693beb208ff
common : more accurate sampling timing (#17382)

* common : more accurate sampling timing

* eval-callback : minor fixes

* cont : add time_meas impl

* cont : fix log msg [no ci]

* cont : fix multiple definitions of time_meas

* llama-cli : exclude chat template init from time measurement

* cont : print percentage of unaccounted time

* cont : do not reset timings
common/common.cpp
common/common.h
common/sampling.cpp
examples/eval-callback/eval-callback.cpp
src/llama-impl.cpp
src/llama-sampling.cpp
tools/main/main.cpp