v0.0.1
版本发布时间: 2023-07-10 18:39:12
xorbitsai/inference最新发布版本:v1.0.0(2024-11-15 18:15:44)
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 https://github.com/xorbitsai/inference/pull/3
- FEAT: support wizardlm by @UranusSeven in https://github.com/xorbitsai/inference/pull/14
- FEAT: baichuan by @UranusSeven in https://github.com/xorbitsai/inference/pull/16
- FEAT: gradio prototype by @aresnow1 in https://github.com/xorbitsai/inference/pull/15
- FEAT: stream generation by @UranusSeven in https://github.com/xorbitsai/inference/pull/17
- FEAT: distributed framework by @UranusSeven in https://github.com/xorbitsai/inference/pull/25
- FEAT: local deployment by @UranusSeven in https://github.com/xorbitsai/inference/pull/38
- FEAT: custom system prompt by @UranusSeven in https://github.com/xorbitsai/inference/pull/35
- FEAT: support orca by @UranusSeven in https://github.com/xorbitsai/inference/pull/51
- FEAT: localization language support by @aresnow1 in https://github.com/xorbitsai/inference/pull/63
- FEAT: Generate through cmdline by @RayJi01 in https://github.com/xorbitsai/inference/pull/70
- FEAT: async client by @UranusSeven in https://github.com/xorbitsai/inference/pull/73
- FEAT: RESTful API by @jiayini1119 in https://github.com/xorbitsai/inference/pull/40
- FEAT: Support Command Line Operation for Chat functionality by @RayJi01 in https://github.com/xorbitsai/inference/pull/74
- FEAT: Support chatglm-6b by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/75
- FEAT: add both versions of chatglm by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/90
- FEAT: slot based model allocation by @UranusSeven in https://github.com/xorbitsai/inference/pull/108
Enhancements
- ENH: Streaming chat UI by @aresnow1 in https://github.com/xorbitsai/inference/pull/31
- ENH: Add checkbox to show stop reason & window size of chat history by @aresnow1 in https://github.com/xorbitsai/inference/pull/44
- ENH: disable stream by default by @UranusSeven in https://github.com/xorbitsai/inference/pull/68
- ENH: Report worker status to supervisor periodically by @aresnow1 in https://github.com/xorbitsai/inference/pull/78
- ENH: unify gradio and fastapi by @jiayini1119 in https://github.com/xorbitsai/inference/pull/88
- ENH: Add download progress if model is not cached by @aresnow1 in https://github.com/xorbitsai/inference/pull/95
- ENH: edit Llama parameters by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/98
- ENH: Support alpaca Chinses by @RayJi01 in https://github.com/xorbitsai/inference/pull/105
- ENH: optimize xinference cmdline by @pangyoki in https://github.com/xorbitsai/inference/pull/103
- ENH: Use thread to launch server by @aresnow1 in https://github.com/xorbitsai/inference/pull/104
- ENH: Add meta file to check if model is downloaded by @aresnow1 in https://github.com/xorbitsai/inference/pull/107
- ENH: basic exception handling for RESTful api by @UranusSeven in https://github.com/xorbitsai/inference/pull/111
- ENH: client provides chat and gen interface by @UranusSeven in https://github.com/xorbitsai/inference/pull/117
- ENH: logging for subprocess by @aresnow1 in https://github.com/xorbitsai/inference/pull/119
- BLD: fix pre-commit by @UranusSeven in https://github.com/xorbitsai/inference/pull/2
- BLD: Add workflow for uploading to PyPI by @aresnow1 in https://github.com/xorbitsai/inference/pull/92
- REF: refactor model spec by @UranusSeven in https://github.com/xorbitsai/inference/pull/45
- REF: change completion type for RESTful API by @UranusSeven in https://github.com/xorbitsai/inference/pull/56
- REF: refactor chat history for restful api by @UranusSeven in https://github.com/xorbitsai/inference/pull/64
- REF: pass model uid and spec to model by @UranusSeven in https://github.com/xorbitsai/inference/pull/85
- REF: rename package by @UranusSeven in https://github.com/xorbitsai/inference/pull/89
Bug fixes
- BUG: Missing dependencies by @jiayini1119 in https://github.com/xorbitsai/inference/pull/21
- BUG: fix controller cmdline by @UranusSeven in https://github.com/xorbitsai/inference/pull/48
- BUG: fix mypy by @UranusSeven in https://github.com/xorbitsai/inference/pull/67
- BUG: RESTful api actor cannot exit by @UranusSeven in https://github.com/xorbitsai/inference/pull/83
- BUG: too many clients by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/87
- BUG: fix chat_history type by @pangyoki in https://github.com/xorbitsai/inference/pull/106
- BUG: Raise KeyError when get model which is not launched by @aresnow1 in https://github.com/xorbitsai/inference/pull/109
- BUG: fix chatglm download url by @UranusSeven in https://github.com/xorbitsai/inference/pull/110
- BUG: load chatglm by @UranusSeven in https://github.com/xorbitsai/inference/pull/112
- BUG: worker timeout during downloading by @UranusSeven in https://github.com/xorbitsai/inference/pull/126
- BUG: fix example by @UranusSeven in https://github.com/xorbitsai/inference/pull/130
- BUG: remove chinese_alpaca model by @pangyoki in https://github.com/xorbitsai/inference/pull/128
- BUG: Use sync client in gradio by @aresnow1 in https://github.com/xorbitsai/inference/pull/129
- BUG: chatglm hangs by @UranusSeven in https://github.com/xorbitsai/inference/pull/118
- BUG: add error handling when the endpoint port is not available by @jiayini1119 in https://github.com/xorbitsai/inference/pull/127
- BUG: fix default host in cmdline by @pangyoki in https://github.com/xorbitsai/inference/pull/132
Tests
- TST: lint by @UranusSeven in https://github.com/xorbitsai/inference/pull/55
- TST: fix mypy by @UranusSeven in https://github.com/xorbitsai/inference/pull/57
- TST: asyncio mode auto by @UranusSeven in https://github.com/xorbitsai/inference/pull/66
- TST: CI by @UranusSeven in https://github.com/xorbitsai/inference/pull/71
- TST: add chatglm tests by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/97
- TST: Add tests for RESTful API by @jiayini1119 in https://github.com/xorbitsai/inference/pull/134
Documentation
- DOC: issue template by @UranusSeven in https://github.com/xorbitsai/inference/pull/76
- DOC: readme by @UranusSeven in https://github.com/xorbitsai/inference/pull/121
- DOC: roadmap by @UranusSeven in https://github.com/xorbitsai/inference/pull/131
- DOC: license by @UranusSeven in https://github.com/xorbitsai/inference/pull/133
Others
- Pass chat history when calling
model.generate
by @aresnow1 in https://github.com/xorbitsai/inference/pull/24 - Rename some classes and files by @aresnow1 in https://github.com/xorbitsai/inference/pull/59
- Fix stop reason by @aresnow1 in https://github.com/xorbitsai/inference/pull/60
- add error message while worker timeout by @pangyoki in https://github.com/xorbitsai/inference/pull/125
New Contributors
- @UranusSeven made their first contribution in https://github.com/xorbitsai/inference/pull/2
- @aresnow1 made their first contribution in https://github.com/xorbitsai/inference/pull/15
- @jiayini1119 made their first contribution in https://github.com/xorbitsai/inference/pull/21
- @RayJi01 made their first contribution in https://github.com/xorbitsai/inference/pull/70
- @Bojun-Feng made their first contribution in https://github.com/xorbitsai/inference/pull/75
- @pangyoki made their first contribution in https://github.com/xorbitsai/inference/pull/103
Full Changelog: https://github.com/xorbitsai/inference/commits/v0.0.1