Skip to content

Releases: TabbyML/tabby

v0.6.0-rc.0

23 Nov 01:50
Compare
Choose a tag to compare
v0.6.0-rc.0 Pre-release
Pre-release

πŸš€ Features

πŸ‘· Built-in distribution support: running completion / chat model worker on different process / machine.

image

The community edition has a restriction of a maximum of one worker for code completion/chat. The enterprise edition is still in private alpha and is only available to our design partners. If you're interested, please DM Meng Zhang on the Slack channel to apply (limited slots available).

πŸ’¬ Conversation history in chat playground.

image

🧰 Fixes and Improvements

  • Fix the slow repository indexing due to constraint memory arena in tantivy index writer.
  • Command line argument --model is now optional, so users can create a chat only instance.
  • New command line argument --parallelism to control the throughput and VRAM usage: #727
  • New api path/metrics endpoint for prometheus metrics collection.

πŸ’« New Contributors

Full Changelog: v0.5.5...v0.6.0-rc.0

v0.5.5

09 Nov 08:46
Compare
Choose a tag to compare

⚠️ Notice

  • llama.cpp backend (CPU, Metal) now requires a redownload of gguf model due to upstream format changes: #645 ggerganov/llama.cpp#3252
  • Due to indexing format changes, the ~/.tabby/index needs to be manually removed before any further runs of tabby scheduler.
  • TABBY_REGISTRY is replaced with TABBY_DOWNLOAD_HOST for the github based registry implementation.

πŸš€ Features

  • Improved dashboard UI.
image

🧰 Fixes and Improvements

  • Cpu backend is switched to llama.cpp: #638
  • add server.completion_timeout to control the code completion interface timeout: #637
  • Cuda backend is switched to llama.cpp: #656
  • Tokenizer implementation is switched to llama.cpp, so tabby no longer need to download additional tokenizer file: #683

πŸ’« New Contributors

Full Changelog: v0.4.0...v0.5.5

v0.5.4

07 Nov 21:36
Compare
Choose a tag to compare
v0.5.4 Pre-release
Pre-release

🧰 Fixes and Improvements

  • Fix deadlock issue reported in #718

v0.5.3

07 Nov 09:24
Compare
Choose a tag to compare
v0.5.3 Pre-release
Pre-release

⚠️ Notice

  • llama.cpp backend (CPU, Metal) now requires a redownload of gguf model due to upstream format changes: #645 ggerganov/llama.cpp#3252
  • Due to indexing format changes, the ~/.tabby/index needs to be manually removed before any further runs of tabby scheduler.
  • TABBY_REGISTRY is replaced with TABBY_DOWNLOAD_HOST for the github based registry implementation.

πŸš€ Features

  • Improved dashboard UI.
image

🧰 Fixes and Improvements

  • Cpu backend is switched to llama.cpp: #638
  • add server.completion_timeout to control the code completion interface timeout: #637
  • Cuda backend is switched to llama.cpp: #656
  • Tokenizer implementation is switched to llama.cpp, so tabby no longer need to download additional tokenizer file: #683

πŸ’« New Contributors

Full Changelog: v0.4.0...v0.5.3

v0.5.2-rc.0

07 Nov 07:32
Compare
Choose a tag to compare
v0.5.2-rc.0 Pre-release
Pre-release
v0.5.2-rc.0

v0.5.2

07 Nov 08:57
Compare
Choose a tag to compare
v0.5.2 Pre-release
Pre-release
Release 0.5.2

http-api-bindings@0.5.2
llama-cpp-bindings@0.5.2
tabby@0.5.2
tabby-common@0.5.2
tabby-download@0.5.2
tabby-inference@0.5.2
tabby-scheduler@0.5.2

Generated by cargo-workspaces

v0.5.1-rc.2

05 Nov 20:30
Compare
Choose a tag to compare
v0.5.1-rc.2 Pre-release
Pre-release
v0.5.1-rc.2

v0.5.1-rc.1

05 Nov 20:09
Compare
Choose a tag to compare
v0.5.1-rc.1 Pre-release
Pre-release
v0.5.1-rc.1

v0.5.0-rc.4

04 Nov 01:02
Compare
Choose a tag to compare
v0.5.0-rc.4 Pre-release
Pre-release
v0.5.0-rc.4

v0.5.0

04 Nov 01:39
Compare
Choose a tag to compare
v0.5.0 Pre-release
Pre-release
Release 0.5.0

http-api-bindings@0.5.0
llama-cpp-bindings@0.5.0
tabby@0.5.0
tabby-common@0.5.0
tabby-download@0.5.0
tabby-inference@0.5.0
tabby-scheduler@0.5.0

Generated by cargo-workspaces