]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
sync : ggml (#5452)
authorGeorgi Gerganov <redacted>
Mon, 12 Feb 2024 07:16:06 +0000 (09:16 +0200)
committerGitHub <redacted>
Mon, 12 Feb 2024 07:16:06 +0000 (09:16 +0200)
commit3b169441dfe8e420f88d1592708cc2a871daadb9
treeb554c9eac1b3b7dbf11e364b6a4a748605a6e949
parent3bdc4cd0f595a6096cca4a64aa75ffa8a3503465
sync : ggml (#5452)

* ggml-alloc : v3 (ggml/727)

* ggml-alloc v3

ggml-ci

* fix ci

ggml-ci

* whisper : check for backend buffer allocation failures

* whisper : avoid leaks when initialization fails

* cleanup

ggml-ci

* style fixes

ggml-ci

* sync : ggml

* update llama.cpp, clip.cpp, export-lora.cpp

* update finetune.cpp, train-text-from-scratch.cpp

ggml-ci

* ggml-backend : reduce alignment to 32 to match gguf and fix mmap

---------

Co-authored-by: slaren <redacted>
12 files changed:
examples/export-lora/export-lora.cpp
examples/finetune/finetune.cpp
examples/llava/clip.cpp
examples/train-text-from-scratch/train-text-from-scratch.cpp
ggml-alloc.c
ggml-alloc.h
ggml-backend.c
ggml-backend.h
ggml.c
ggml.h
llama.cpp
scripts/sync-ggml.last