ggml: bump submodule for full CUDA GET_ROWS type coverage

Browse Source

i-quants and mxfp4 join the k-quants on the direct device path, bringing
CUDA to parity with the Metal, Vulkan and SYCL backends.

...

This commit is contained in:

Pascal

2026-07-19 22:30:22 +02:00

parent e93292bee1

commit fbff3317a4

1 changed files with 1 additions and 1 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

+1 -1

Submodule ggml updated: f9f45e143d...69cf6fea5d