diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-06-05 08:30:35 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-05 08:30:35 +0300 |
| commit | 0b10f7418f7315ef90e35da49e0c053b395fd528 (patch) | |
| tree | f5210b364436da3aa058a2c3c4f665aff2200470 /examples/server/webui/src/main.tsx | |
| parent | 7e79665a31129597634bcef403512aaf4fcdeef9 (diff) | |
Faster CPU prompt processing for Trellis quants and MoE models (#488)
* Also do the dequantize approach for mul_mat_id
* Also do the dequantize approach for iqk_moe_fused_up_gate
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/server/webui/src/main.tsx')
0 files changed, 0 insertions, 0 deletions