v0.1.0

版本发布时间: 2023-07-28 21:13:01

xorbitsai/inference最新发布版本:v1.1.0(2024-12-13 18:29:37)

What's new in 0.1.0 (2023-07-28)

These are the changes in inference v0.1.0.

FEAT: support fp4 and int8 quantization for pytorch model by @pangyoki in https://github.com/xorbitsai/inference/pull/238
FEAT: support llama-2-chat-70b ggml by @UranusSeven in https://github.com/xorbitsai/inference/pull/257

ENH: skip 4-bit quantization for non-linux or non-cuda local deployment by @UranusSeven in https://github.com/xorbitsai/inference/pull/264
ENH: handle legacy cache by @UranusSeven in https://github.com/xorbitsai/inference/pull/266
REF: model family by @UranusSeven in https://github.com/xorbitsai/inference/pull/251

BUG: fix restful stop parameters by @RayJi01 in https://github.com/xorbitsai/inference/pull/241
BUG: download integrity hot fix by @RayJi01 in https://github.com/xorbitsai/inference/pull/242
BUG: disable baichuan-chat and baichuan-base on macos by @pangyoki in https://github.com/xorbitsai/inference/pull/250
BUG: delete tqdm_class in snapshot_download by @pangyoki in https://github.com/xorbitsai/inference/pull/258
BUG: ChatGLM Parameter Switch by @Bojun-Feng in https://github.com/xorbitsai/inference/pull/262
BUG: refresh related fields when format changes by @UranusSeven in https://github.com/xorbitsai/inference/pull/265
BUG: Show downloading progress in gradio by @aresnow1 in https://github.com/xorbitsai/inference/pull/267
BUG: LLM json not included by @UranusSeven in https://github.com/xorbitsai/inference/pull/268

DOC: Update installation part in readme by @aresnow1 in https://github.com/xorbitsai/inference/pull/253
DOC: update readme for pytorch model by @pangyoki in https://github.com/xorbitsai/inference/pull/207

Full Changelog: https://github.com/xorbitsai/inference/compare/v0.0.6...v0.1.0