github ggml-org/llama.cpp b7300

latest releases: b7310, b7307, b7306...
14 hours ago

Warning

Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

vulkan: Use one row per workgroup for f32 mmv (#17711)

The MoE models have a mul_mat_vec with very small m (32, 64, 128) right before
the topk_moe selection. Running multiple rows per wg doesn't utilize the SMs
well. I think even for larger m, f32 is so bandwidth-limited that running
multiple rows doesn't help.

macOS/iOS:

Linux:

Windows:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.