Training-free amplitude outlier suppression for Transformer Q/O projections, with a measured cost.
Compress Transformer time-series KV cache tensors as high-dimensional multimedia image signals: JPEG-style lossy frequency domain (DCT) plus PNG-style lossless time-domain deltas
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page