What's Changed

• Update README.md by Yang Wang (@YangWang92) in #167
• refactor (csrc): Restructure C++ code organization to facilitate adding new kernels by Cao Ying (@lcy-seso) in #169
• [pack save] fix save cpu offloda model by wejoncy in #177
• fix bug on logger res_index by Yang Wang (@YangWang92) in #178
• Update README.md by Yang Wang (@YangWang92) in #179
• add index bitwidth=10 by Yang Wang (@YangWang92) in #181

Full Changelog: v0.0.5...v0.0.5post1

What's Changed

• Update README.md by Yang Wang (@YangWang92) in #127
• Update README.md by wejoncy in #129
• Update vptq_example.ipynb by Yang Wang (@YangWang92) in #138
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #141
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #142
• update huggingface transformers support by Yang Wang (@YangWang92) in #143
• Update README.md by Yang Wang (@YangWang92) in #144
• refactor: refactor and optimize python code implementations. by Cao Ying (@lcy-seso) in #145
• Update README.md by Yang Wang (@YangWang92) in #146
• fix: a small bug fix for the initialization of the residual index tensor. by Cao Ying (@lcy-seso) in #147
• fix(build): build using cmake. by Cao Ying (@lcy-seso) in #149
• update setuptools version by Yang Wang (@YangWang92) in #151
• fix: Fix the bug where the Torch library is not correctly linked. by Cao Ying (@lcy-seso) in #152
• update version by Yang Wang (@YangWang92) in #153
• fix loading by wejoncy in #154
• fix perm by wejoncy in #157
• add tools by wejoncy in #158
• quick fix by wejoncy in #160
• Update README.md by wejoncy in #161
• fix(build): fix the undefined symbols runtime error. by Cao Ying (@lcy-seso) in #162
• fix(cmake): building dynamic library for specified GPU architectures and support multi threads compile by Cao Ying (@lcy-seso) in #164
• bump to 0.0.5 by wejoncy in #165
• fix(csrc): Remove strong dependency on specific Torch version. by Cao Ying (@lcy-seso) in #166

New Contributors

• Cao Ying (@lcy-seso) made their first contribution in #145

Full Changelog: v0.0.4...v0.0.5

What's Changed

• Update README.md by Yang Wang (@YangWang92) in #108
• Update README.md by Yang Wang (@YangWang92) in #109
• Add CUDA_HOME instructions to README by Caron (@caronzh03) in #112
• Update README.md by Yang Wang (@YangWang92) in #117
• fix config format for transformers by wejoncy in #120
• Bump to 0.0.4 by wejoncy in #121
• fix version__ by wejoncy in #122
• fix setup version number by wejoncy in #123
• Update model_base.py by Yang Wang (@YangWang92) in #124

New Contributors

• Caron (@caronzh03) made their first contribution in #112

Full Changelog: v0.0.3...v0.0.4

What's Changed

• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #40
• Update README.md by Yang Wang (@YangWang92) in #43
• add sm_89 by wejoncy in #45
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #46
• add notebook by Yang Wang (@YangWang92) in #48
• docs: update README.md by Ikko Eltociear Ashimine (@eltociear) in #47
• add catlog and index for readme by wejoncy in #49
• support bf16 by wejoncy in #51
• add gpu monitor at web app by TITC (@TITC) in #50
• update installation by wejoncy in #55
• Delete models directory by Yang Wang (@YangWang92) in #58
• fix offload bug in accelerator by wejoncy in #60
• Revert "fix offload bug in accelerator" by wejoncy in #61
• support rocm by wejoncy in #63
• rocm fix by wejoncy in #65
• improve web app demo by Yang Wang (@YangWang92) in #66
• Update setup.py by Yang Wang (@YangWang92) in #68
• refine online demo by Yang Wang (@YangWang92) in #69
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #70
• Update setup.py by Yang Wang (@YangWang92) in #72
• update device map by Yang Wang (@YangWang92) in #74
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #80
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #81
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #82
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #83
• add math example by Yang Wang (@YangWang92) in #84
• add acknowledgement and disclaimer by Yang Wang (@YangWang92) in #85
• Update README.md by Yang Wang (@YangWang92) in #94
• fix format by Yang Wang (@YangWang92) in #95
• Use absolute imports by Brando Tovar (@bndos) in #90
• Set version by Yang Wang (@YangWang92) in #97
• fix compiling error by Yang Wang (@YangWang92) in #98
• Update vqlinear.py by laomao0 in #103
• add package info by Yang Wang (@YangWang92) in #104
• update pyproject by Yang Wang (@YangWang92) in #106

New Contributors

• Ikko Eltociear Ashimine (@eltociear) made their first contribution in #47
• TITC (@TITC) made their first contribution in #50
• Brando Tovar (@bndos) made their first contribution in #90
• laomao0 made their first contribution in #103

Full Changelog: v0.0.2...v0.0.3

What's Changed

• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #40
• Update README.md by Yang Wang (@YangWang92) in #43
• add sm_89 by wejoncy in #45
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #46
• add notebook by Yang Wang (@YangWang92) in #48
• docs: update README.md by Ikko Eltociear Ashimine (@eltociear) in #47
• add catlog and index for readme by wejoncy in #49
• support bf16 by wejoncy in #51
• add gpu monitor at web app by TITC (@TITC) in #50

New Contributors

• Ikko Eltociear Ashimine (@eltociear) made their first contribution in #47
• TITC (@TITC) made their first contribution in #50

Full Changelog: v0.0.2...v0.0.2.post1

What's Changed

• Update README.md by Yang Wang (@YangWang92) in #22
• Update README.md by Yang Wang (@YangWang92) in #25
• Patch 1 by OpenSourceRonin (@OpenSourceRonin) in #27
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #28
• Update README.md by Yang Wang (@YangWang92) in #30
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #31
• Update README.md by Yang Wang (@YangWang92) in #32
• Update README.md by Yang Wang (@YangWang92) in #33
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #34
• Update README.md by OpenSourceRonin (@OpenSourceRonin) in #35
• add prompt args and check cuda kernel by Yang Wang (@YangWang92) in #36
• update readme and tech report by Yang Wang (@YangWang92) in #37
• support cuda-arch_list by wejoncy in #38
• bump to 0.0.2 by wejoncy in #39

Full Changelog: v0.0.1...v0.0.2

What's Changed

• add Acknowledgement by Yang Wang (@YangWang92) in #14
• gradio app by wejoncy in #16
• Update README.md by Yang Wang (@YangWang92) in #18
• publish ci by wejoncy in #17
• Bias by wejoncy in #19
• fix out of bound error by wejoncy in #20
• Add open source community by OpenSourceRonin (@OpenSourceRonin) in #21
• memory and bf16 by wejoncy in #23

New Contributors

• OpenSourceRonin (@OpenSourceRonin) made their first contribution in #21

Full Changelog: https://github.com/microsoft/VPTQ/commits/v0.0.1