Skip to content

Releases: basetenlabs/truss

v0.4.2

01 Jul 14:02
2adbc39
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.4.1...v0.4.2

v0.4.1

01 Jul 14:01
56038cb
Compare
Choose a tag to compare

What's Changed

Full Changelog: v0.4.0...v0.4.1

v0.4.0

01 Jul 14:00
fdf9c1b
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: v0.3.2...v0.4.0

v0.3.2

03 Feb 14:32
a4d4dbe
Compare
Choose a tag to compare

Bug fix for draft models for older versions of python

v0.2.0

20 Jan 18:21
73ed2aa
Compare
Choose a tag to compare

With this release, a minor version increment recognizes the overall progress made on Truss since its initial release in Summer 2022. And simplified naming for key functions improves Truss' developer experience, while carefully considered warnings and a long deprecation period ensure nothing breaks.

Interface changes

  • In the Python client, truss.create() replaces truss.mk_truss().
  • In the Python client, truss.load() replaces truss.from_directory().
  • In the Truss handle, truss.predict() offers a shorter alternative to truss.server_predict(). To use in place of truss.docker_predict(), pass the optional kwarg use_docker=True.
  • In the command-line interface, the behavior of truss predict has been updated to match the Python client.
    • Previously, truss predict ran on Docker by default, which could be overriden with RUN_LOCAL=true.
    • Now, truss predict runs without Docker by default, which can be overriden with USE_DOCKER=true.

These interface changes are intended to improve Truss' developer experience, not cause unnecessary trouble. As such, the old mk_truss() and from_directory() functions, while marked with a deprecation warning, will not be removed until the next major version update. And both server_predict() and docker_predict() will be supported in the Truss handle indefinitely.

v0.1.13rc2

03 Jan 19:37
6990b96
Compare
Choose a tag to compare
v0.1.13rc2 Pre-release
Pre-release

Failed models should shut down server
Solve python requirements inference

v0.1.13rc1

23 Dec 01:02
4cadc10
Compare
Choose a tag to compare
v0.1.13rc1 Pre-release
Pre-release
Only kill process on failed load if not live_reload (#166)

don't kill the process when live reload is enabled

v0.1.12

22 Dec 00:06
a22eb78
Compare
Choose a tag to compare

If model load fails, bring down the tornado server.

v0.1.11

20 Dec 18:58
b6d3b28
Compare
Choose a tag to compare

Remove automatically adding numpy dependency for files
Fix break for numpy v1.24

v0.1.7: increase wait and retries (#129)

22 Nov 01:57
4325f8c
Compare
Choose a tag to compare
* increase wait and retries

* add server wait retries

* bump version