Skip to content

Releases: instill-ai/model-backend

v0.21.2-alpha

25 Jan 22:10
2e74b79
Compare
Choose a tag to compare
v0.21.2-alpha Pre-release
Pre-release

0.21.2-alpha (2024-01-25)

Bug Fixes

  • main: fix misused return statement (5cbfc3d)

v0.21.1-alpha

02 Jan 14:25
8ec74e3
Compare
Choose a tag to compare
v0.21.1-alpha Pre-release
Pre-release

0.21.1-alpha (2024-01-02)

Features

  • service: support basic github pat to avoid rate-limit (#477) (45931ca)

Miscellaneous Chores

  • release: release v0.21.1-alpha (bd320b0)

v0.21.0-alpha

15 Dec 16:54
014b26a
Compare
Choose a tag to compare
v0.21.0-alpha Pre-release
Pre-release

0.21.0-alpha (2023-12-14)

Features

  • model: refactoring AI Tasks for Consistency Across Text and Image Generation (#461) (e827130)
  • redis: use redis for model state caching (#472) (3b6b977)

Bug Fixes

  • model: fix grpc message size limit issue (#474) (1ec7ae1)

v0.20.0-alpha

30 Nov 11:42
47e6e31
Compare
Choose a tag to compare
v0.20.0-alpha Pre-release
Pre-release

0.20.0-alpha (2023-11-30)

Features

  • model: Enhancements for Image Inpu in Text 2 Image Task (#457) (eb604a1)
  • ray: use shared python executable (#455) (db9658b)

Bug Fixes

v0.19.0-alpha

11 Nov 11:30
850aa90
Compare
Choose a tag to compare
v0.19.0-alpha Pre-release
Pre-release

0.19.0-alpha (2023-11-11)

Features

  • model: Support New Fields for Multi-Modal Model In Text Generation Task and Refactor Existing Ones (#448) (49bdf5b)
  • ray: add ray serve as model serving backend (#445) (a9b4005)

Bug Fixes

  • predeploy: fix predeploy model missing triton models reference (3f296cd)
  • ray: fix model healthcheck causing scaling loop (#450) (4d8cdbf)
  • ray: fix unziping ray model (ca79411)
  • service: fix fail model deletion in state error (#449) (91125c0)

v0.18.0-alpha

27 Oct 11:05
c6f255f
Compare
Choose a tag to compare
v0.18.0-alpha Pre-release
Pre-release

0.18.0-alpha (2023-10-26)

Features

  • model: Enhancements for Llava Model Support and Model Hub File Movement (#434) (58cb97c)
  • model: Support for LLM-like models in TRITON Inference Server (#432) (590eb0b)

Bug Fixes

  • Dockerfile: fix Python 3.11 using Debian base image (#438) (2ace6eb)
  • payload: fix incorrect conversion between integer types (#440) (32bffea)

v0.17.2-alpha

13 Oct 05:31
9fa51e3
Compare
Choose a tag to compare
v0.17.2-alpha Pre-release
Pre-release

0.17.2-alpha (2023-10-13)

Bug Fixes

  • model: fix init model namespace (77a35b3)

v0.17.1-alpha

30 Sep 13:47
f4d3a82
Compare
Choose a tag to compare
v0.17.1-alpha Pre-release
Pre-release

0.17.1-alpha (2023-09-30)

Bug Fixes

  • main: fix namespace error when deploying model (#423) (dd5badf)

v0.17.0-alpha

13 Sep 09:44
cb5e144
Compare
Choose a tag to compare
v0.17.0-alpha Pre-release
Pre-release

0.17.0-alpha (2023-09-13)

Miscellaneous Chores

  • release: release v0.17.0-alpha (70172a2)
  • chore: adopt api-gateway merge (c65a91a)
  • chore: remove api-token validation (aa34403)
  • refactor: support namespace endpoints (6e94cb1)

v0.16.11-alpha

19 Aug 07:11
a6034fc
Compare
Choose a tag to compare
v0.16.11-alpha Pre-release
Pre-release

0.16.11-alpha (2023-08-19)

Miscellaneous Chores

  • release: release v0.16.11-alpha (5aba1ce)
  • refactor: refactor(controller) remove most dependencies from controller (b7b36a6)