]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml : sync llama.cpp (memory allocator + cuda + metal)
authorGeorgi Gerganov <redacted>
Mon, 7 Aug 2023 09:09:58 +0000 (12:09 +0300)
committerGeorgi Gerganov <redacted>
Mon, 7 Aug 2023 11:23:05 +0000 (14:23 +0300)
commitb95f6f7f86acdc4cf0bc75f2cc327f65403c3915
treee37e71586206b16570da859d42a81048e3ce7560
parenta30107764ca5544e3a1ead4b318e06d83ed5b14c
ggml : sync llama.cpp (memory allocator + cuda  + metal)

ggml-ci
13 files changed:
examples/mnist/main-cpu.cpp
include/ggml/ggml.h
scripts/sync-llama.sh
src/ggml-cuda.cu
src/ggml-cuda.h
src/ggml-metal.m
src/ggml-metal.metal
src/ggml.c
tests/CMakeLists.txt
tests/test-grad0.c [deleted file]
tests/test-grad0.cpp [new file with mode: 0644]
tests/test-opt.c [deleted file]
tests/test-opt.cpp [new file with mode: 0644]