Lossless AI compression: 33% less GPU memory, bit for bit. Models load with their weights packed on the GPU (glyd.from_pretrained); a codec for files and object storage.
Glyd on the GPU: a bf16 model's weights held compressed in GPU memory, bit for bit, and multiplied from there. The GPU half of glyd (pip install "glyd[gpu]"), compiled.
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