FlashML
Maker · 1 entry
Everything from FlashML
| Name | What to know | Price or memory | |
|---|---|---|---|
| Edge-native MoE serving engine keeps most experts in system RAM and moves only needed experts to the GPU, so huge MoE models run on one consumer GPU. | |||
Maker · 1 entry
| Name | What to know | Price or memory | |
|---|---|---|---|
| Edge-native MoE serving engine keeps most experts in system RAM and moves only needed experts to the GPU, so huge MoE models run on one consumer GPU. | |||