srep-moe
Expert-Aware Multi-Batch Pipeline for MoE + Speculative Decoding inference optimization (CPU-PCIe-GPU).
Activity
- Latest release
- 6mo ago
- Total releases
- 1
- Cadence
- —
- Last 12 months
- 1
Details
- License
- Apache-2.0
- First release
- Mar 09, 2026
Expert-Aware Multi-Batch Pipeline for MoE + Speculative Decoding inference optimization (CPU-PCIe-GPU).