ReleaseReplicateReplicatepublished Sep 22, 2026seen 2w

replicate/cog v0.23.0

replicate/cog

Open original ↗

Captured source

source ↗
published Sep 22, 2026seen 2wcaptured 2whttp 200method plain

v0.23.0

Repository: replicate/cog

Tag: v0.23.0

Published: 2026-09-22T22:05:11Z

Prerelease: no

Release notes:

New features

  • GPU compatibility warnings in `cog doctor`. cog doctor now warns when the resolved PyTorch and CUDA wheel ships no kernels for the local GPU, catching images that build successfully but fail when they run CUDA operations. (#3104)
  • OpenTelemetry tracing. Models can opt into distributed traces spanning Cog's HTTP server, parent and worker processes, and Python model code. Cog continues incoming W3C trace context, exports through OTLP, and leaves tracing disabled by default. (#3157)
  • JSON output for `cog push`. cog push --json emits one versioned JSON document with digest-pinned image, model, and managed-weight references for image and bundle projects. Progress and diagnostics remain on stderr. (#3178)

Improvements

  • `.dockerignore` guidance. The getting-started documentation now explains Cog's Docker build context and how to exclude development-only files to reduce build time and image size. (#3165)

Bug fixes

  • CUDA 13 builds work with uv-managed Python. Cog now passes --break-system-packages and creates the expected python alias for both prebuilt and direct CUDA 13 base images. (#3160)

Excerpt shown — open the source for the full document.