moe
for LLM engineers
Why this scored 9
every term, weightedIts fastest-moving item, measured against the pace of its own source
Whether that velocity is itself speeding up, as a per-hour rate
How many independent communities its own items come from
Decays to zero over 14 days, counted from when we first saw it
Subtracted once something is big and old — sized by its biggest item, aged from when we first saw it
Weights are hand-tuned, not learned — we're calibrating them against realized trends as history accumulates. On an entity's first sighting there's no previous reading to compare against, so acceleration starts from a neutral prior rather than a measurement, and velocity falls back to engagement over its whole lifetime until a second reading exists. Full methodology
Signal history
7-day window (free)The evidence
The live items this entity's score aggregates — every community independently talking about it right now. This is the corroboration, shown, not claimed.
- 119
ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs
ACE enables calibration-free expert skipping in MoE LLMs, cutting inference overhead. · for LLM engineers
arxivSteadyai4d ago - 29
MMOE: Modernizing Diffusion Transformers with Efficient Expert Design
Diffusion transformers improved · for ai researchers, nlp devs
arxivSteadyai45d ago - 37
PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization
Efficient LLM serving method · for ai researchers
arxivSteadyai53d ago