ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels

Browse source

* added fallback mechanism when the offline re-quantized model is not
optimized for the underlying target.

...

This commit is contained in:

Charles Xu 2024-08-28 10:18:31 +02:00

parent 3d6bf6919f

commit baad96a363

1 changed files with 1119 additions and 1089 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

2208

ggml/src/ggml-aarch64.c

View file

File diff suppressed because it is too large Load diff