What's new in 0.0.1 (2023-07-10)
These are the changes in inference v0.0.1.
New features
- FEAT: prototype by @UranusSeven in #3
- FEAT: support wizardlm by @UranusSeven in #14
- FEAT: baichuan by @UranusSeven in #16
- FEAT: gradio prototype by @aresnow1 in #15
- FEAT: stream generation by @UranusSeven in #17
- FEAT: distributed framework by @UranusSeven in #25
- FEAT: local deployment by @UranusSeven in #38
- FEAT: custom system prompt by @UranusSeven in #35
- FEAT: support orca by @UranusSeven in #51
- FEAT: localization language support by @aresnow1 in #63
- FEAT: Generate through cmdline by @RayJi01 in #70
- FEAT: async client by @UranusSeven in #73
- FEAT: RESTful API by @jiayini1119 in #40
- FEAT: Support Command Line Operation for Chat functionality by @RayJi01 in #74
- FEAT: Support chatglm-6b by @Bojun-Feng in #75
- FEAT: add both versions of chatglm by @Bojun-Feng in #90
- FEAT: slot based model allocation by @UranusSeven in #108
Enhancements
- ENH: Streaming chat UI by @aresnow1 in #31
- ENH: Add checkbox to show stop reason & window size of chat history by @aresnow1 in #44
- ENH: disable stream by default by @UranusSeven in #68
- ENH: Report worker status to supervisor periodically by @aresnow1 in #78
- ENH: unify gradio and fastapi by @jiayini1119 in #88
- ENH: Add download progress if model is not cached by @aresnow1 in #95
- ENH: edit Llama parameters by @Bojun-Feng in #98
- ENH: Support alpaca Chinses by @RayJi01 in #105
- ENH: optimize xinference cmdline by @pangyoki in #103
- ENH: Use thread to launch server by @aresnow1 in #104
- ENH: Add meta file to check if model is downloaded by @aresnow1 in #107
- ENH: basic exception handling for RESTful api by @UranusSeven in #111
- ENH: client provides chat and gen interface by @UranusSeven in #117
- ENH: logging for subprocess by @aresnow1 in #119
- BLD: fix pre-commit by @UranusSeven in #2
- BLD: Add workflow for uploading to PyPI by @aresnow1 in #92
- REF: refactor model spec by @UranusSeven in #45
- REF: change completion type for RESTful API by @UranusSeven in #56
- REF: refactor chat history for restful api by @UranusSeven in #64
- REF: pass model uid and spec to model by @UranusSeven in #85
- REF: rename package by @UranusSeven in #89
Bug fixes
- BUG: Missing dependencies by @jiayini1119 in #21
- BUG: fix controller cmdline by @UranusSeven in #48
- BUG: fix mypy by @UranusSeven in #67
- BUG: RESTful api actor cannot exit by @UranusSeven in #83
- BUG: too many clients by @Bojun-Feng in #87
- BUG: fix chat_history type by @pangyoki in #106
- BUG: Raise KeyError when get model which is not launched by @aresnow1 in #109
- BUG: fix chatglm download url by @UranusSeven in #110
- BUG: load chatglm by @UranusSeven in #112
- BUG: worker timeout during downloading by @UranusSeven in #126
- BUG: fix example by @UranusSeven in #130
- BUG: remove chinese_alpaca model by @pangyoki in #128
- BUG: Use sync client in gradio by @aresnow1 in #129
- BUG: chatglm hangs by @UranusSeven in #118
- BUG: add error handling when the endpoint port is not available by @jiayini1119 in #127
- BUG: fix default host in cmdline by @pangyoki in #132
Tests
- TST: lint by @UranusSeven in #55
- TST: fix mypy by @UranusSeven in #57
- TST: asyncio mode auto by @UranusSeven in #66
- TST: CI by @UranusSeven in #71
- TST: add chatglm tests by @Bojun-Feng in #97
- TST: Add tests for RESTful API by @jiayini1119 in #134
Documentation
- DOC: issue template by @UranusSeven in #76
- DOC: readme by @UranusSeven in #121
- DOC: roadmap by @UranusSeven in #131
- DOC: license by @UranusSeven in #133
Others
- Pass chat history when calling
model.generateby @aresnow1 in #24 - Rename some classes and files by @aresnow1 in #59
- Fix stop reason by @aresnow1 in #60
- add error message while worker timeout by @pangyoki in #125
New Contributors
- @UranusSeven made their first contribution in #2
- @aresnow1 made their first contribution in #15
- @jiayini1119 made their first contribution in #21
- @RayJi01 made their first contribution in #70
- @Bojun-Feng made their first contribution in #75
- @pangyoki made their first contribution in #103
Full Changelog: https://github.com/xorbitsai/inference/commits/v0.0.1