diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-10-31 12:05:27 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-10-31 12:05:27 +0100 |
| commit | 52874c5d21819bd63cc4c500f2fb1be435d16b5e (patch) | |
| tree | bff705dd887d124958d1ad3c224de9ee9732de1a /ggml/src/ggml-common.h | |
| parent | 5ad6439486e5bfdd8e34213a36beb56b74842bbe (diff) | |
Faster MoE inference (#112)
* multi_sdd: WIP
* multi_sdd: CPU works
* multi_add: CUDA
* multi_add: simplify
* multi_add: Metal
* Metal: speed up mul_mat_id
For the Granite-1B MoE model PP-512 goes from
156 t/s to 890 t/s, so nearly a 6X speedup!
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-common.h')
0 files changed, 0 insertions, 0 deletions