diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-10 16:16:51 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-10 16:16:51 +0200 |
| commit | 699c9cb7f63dd8431bce91b86e10efb41255f6c1 (patch) | |
| tree | 6000fd823e443f80f90ec490b1bbdf6461902924 /examples | |
| parent | b096a5de7a9bdf516bb20729d5d0a3b2a12cba2f (diff) | |
Faster MoE token generation on CUDA (#248)
* 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
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples')
0 files changed, 0 insertions, 0 deletions