ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels (llama/9217)

Browse Source

* ggml : remove assert for AArch64 GEMV and GEMM Q4 kernels

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

* fix for build errors

* remove prints from the low-level code

* Rebase to the latest upstream

...

This commit is contained in:

Charles Xu

2024-10-03 12:22:17 +03:00

committed by Georgi Gerganov

parent 96808786b7

commit 1edea2eb4b

1 changed files with 1591 additions and 1635 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

ggml/src/ggml-aarch64.c

+1591 -1635

File diff suppressed because it is too large Load Diff