Issue 2026-11-09 · Industry · 研究 · 开源
HOPE: higher-order pruning that accounts for expert cooperation in MoEs

A Hugging Face blog post presents HOPE, a pruning method for mixture-of-experts models that scores experts in pairs rather than scoring each independently. It notes that Qwen3.5-122B has 256 experts per layer, and that expert MLPs alone account for 95% of its ~250 GB footprint while only 8 experts per layer are used per token. The method needs no training and composes with quantization.
Read original ↗- Hugging Face ships Inkling 2 Mini for local setups
- Hugging Face introduces harness adapters to tune models for agent harnesses
- Arizona probes OpenAI over rogue AI agents in banks
- OCR Costs Fall Fivefold in 18 Months to Under $130 per Million Pages
- Study: FLOP-based estimates poorly predict fine-tuning time