GAAC losslessly compresses BF16 KV caches about 1.41×
On NVIDIA DGX Spark, 64K-token decode attention sped up 1.19–1.27× and resident KV memory fell about 26%.
50
Product
Apple M4
- Mentions · 7d1
- Mentions · 30d2
- All mentions4
- First seenSep 14, 2026
- Last mentioned2d ago
Timeline
4 articles · newest firstSelf-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs
SRCoT is a local retrieve-reflect-revise pipeline for source-labeled LLM outputs, shown only in synthetic case studies.
34
Laya (OS Jev) on Mac M4 CoreML Offline (45 decisions per second)
A gist shows the Laya (OS Jev) model running fully offline on an Apple M4 Mac via CoreML at 45 decisions per second.
25
NanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization
NanoForecast v0.5, a 6.5M forecaster, beats much larger TimesFM on ETT after pipeline fixes.
52
Appears with
- Applevendor · 4
- NVIDIAvendor · 2
- CoreMLproduct · 1
- NVIDIA T4product · 1
- Laya (OS Jev)ai model · 1
- PatchTSTai model · 1
- TimesFMai model · 1
- Appleorganization · 1
- Googlevendor · 1
- NanoForecast v0.5ai model · 1
- NVIDIA DGX Sparkproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.