]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
fit-params : refactor + add option to output estimated memory per device (#22171)
authorGeorgi Gerganov <redacted>
Tue, 21 Apr 2026 06:54:36 +0000 (09:54 +0300)
committerGitHub <redacted>
Tue, 21 Apr 2026 06:54:36 +0000 (09:54 +0300)
commitcfe9838d26aa412e96e6382c93302c379cce7884
tree2c778a88fa24f1c646efdc8ed3119b714078cdfd
parentff6b1062afa9079e36a310b21e9974c4feaff1dc
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
19 files changed:
CODEOWNERS
common/CMakeLists.txt
common/arg.cpp
common/common.cpp
common/common.h
common/fit.cpp [new file with mode: 0644]
common/fit.h [new file with mode: 0644]
common/sampling.cpp
include/llama.h
src/llama-context.cpp
src/llama-context.h
src/llama-ext.h
src/llama-model.cpp
src/llama.cpp
tools/cli/cli.cpp
tools/fit-params/fit-params.cpp
tools/llama-bench/llama-bench.cpp
tools/perplexity/perplexity.cpp
tools/server/server.cpp