]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
metal : pad n_ctx by 32 (#6177)
authorGeorgi Gerganov <redacted>
Fri, 22 Mar 2024 07:36:03 +0000 (09:36 +0200)
committerGitHub <redacted>
Fri, 22 Mar 2024 07:36:03 +0000 (09:36 +0200)
commit95d576b48ebf582b112d1c9cf4eed7142fa4e464
tree1e298e73e8e8de5d7f93d78272f44630fa7198cb
parent59c17f02de8fdf7b084d6100b875b7e2bc07a83b
metal : pad n_ctx by 32 (#6177)

* metal : require ne00 >= 128 for mat-mat kernels

ggml-ci

* llama : pad n_ctx by 32

ggml-ci
common/common.cpp
examples/batched/batched.cpp
llama.cpp
tests/test-backend-ops.cpp