diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-10 16:19:09 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-10 16:19:09 +0200 |
| commit | a48e16324770bb829406d06e11be1df0c8a3b517 (patch) | |
| tree | 1f0ef5e1fd55c35acac40cca85cadc8606dd0673 /examples/batched.swift | |
| parent | 699c9cb7f63dd8431bce91b86e10efb41255f6c1 (diff) | |
DeepSeek imatrix stuff (#250)
* This gives us ~20% TG speedup for DeepSeek on CUDA
* Slightly better
* Also do it for plain (not fused) mul_mat_id
* Guard against numerical precision issues for MLA on CUDA
* imatrix: wv_b <-> wkv_b
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/batched.swift')
0 files changed, 0 insertions, 0 deletions