llama.cpp

LLM-Inference/llama.cpp

Fork 0

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00

Files

T

History

76c956c137 gguf-split: Add option to delete split parts during merge (#26538 )

* Add delete-files option to split parameters

Added a new option to delete split files during execution to free up disk space.

* Add test for delete files on merge option

* Fix tests

* Update tools/gguf-split/gguf-split.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update tools/gguf-split/gguf-split.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Uncomment tests

* Improvements to address PR comments

* Fix formatting

* Fix formatting

* Rename --delete-files to --delete-splits

* Comment tests

* Move delete inside loop

* style cleanup

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

2026-08-04 21:27:47 +03:00

batched-bench

cmake : add install() for impl libraries + fix apple builds (#23511 )

2026-05-22 11:46:26 +03:00

cli

cli : persist reasoning_content in chat history (#26362 )

2026-08-01 18:03:32 +02:00

completion

args: add -lm mlock where it mlocks but doesnt mmap (#26135 )

2026-07-27 16:44:08 +08:00

cvector-generator

libs : rename libcommon -> libllama-common (#21936 )