Fast ONNX-based text, image, and sparse embeddings for Python. Dynamic INT8 ONNX models are ~4x smaller, ~2x lighter in memory and ~1.7-2.0x faster than FP32 on CPU.
Fast, pure-Python full-text indexing, search, and spell checking library.
Taskiq flow for task chaining.
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