Vptq

What's Changed
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/167
* refactor (csrc): Restructure C++ code organization to facilitate adding new kernels by lcy-seso in https://github.com/microsoft/VPTQ/pull/169
* [pack save] fix save cpu offloda model by wejoncy in https://github.com/microsoft/VPTQ/pull/177
* fix bug on logger res_index by YangWang92 in https://github.com/microsoft/VPTQ/pull/178
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/179
* add index bitwidth=10 by YangWang92 in https://github.com/microsoft/VPTQ/pull/181


**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.5...v0.0.5post1

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

New Contributors
* lcy-seso made their first contribution in https://github.com/microsoft/VPTQ/pull/145

**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.4...v0.0.5

What's Changed
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/108
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/109
* Add CUDA_HOME instructions to README by caronzh03 in https://github.com/microsoft/VPTQ/pull/112
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/117
* fix config format for transformers by wejoncy in https://github.com/microsoft/VPTQ/pull/120
* Bump to 0.0.4 by wejoncy in https://github.com/microsoft/VPTQ/pull/121
* fix version__ by wejoncy in https://github.com/microsoft/VPTQ/pull/122
* fix setup version number by wejoncy in https://github.com/microsoft/VPTQ/pull/123
* Update model_base.py by YangWang92 in https://github.com/microsoft/VPTQ/pull/124

New Contributors
* caronzh03 made their first contribution in https://github.com/microsoft/VPTQ/pull/112

**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.3...v0.0.4

What's Changed
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/40
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/43
* add sm_89 by wejoncy in https://github.com/microsoft/VPTQ/pull/45
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/46
* add notebook by YangWang92 in https://github.com/microsoft/VPTQ/pull/48
* docs: update README.md by eltociear in https://github.com/microsoft/VPTQ/pull/47
* add catlog and index for readme by wejoncy in https://github.com/microsoft/VPTQ/pull/49
* support bf16 by wejoncy in https://github.com/microsoft/VPTQ/pull/51
* add gpu monitor at web app by TITC in https://github.com/microsoft/VPTQ/pull/50
* update installation by wejoncy in https://github.com/microsoft/VPTQ/pull/55
* Delete models directory by YangWang92 in https://github.com/microsoft/VPTQ/pull/58
* fix offload bug in accelerator by wejoncy in https://github.com/microsoft/VPTQ/pull/60
* Revert "fix offload bug in accelerator" by wejoncy in https://github.com/microsoft/VPTQ/pull/61
* support rocm by wejoncy in https://github.com/microsoft/VPTQ/pull/63
* rocm fix by wejoncy in https://github.com/microsoft/VPTQ/pull/65
* improve web app demo by YangWang92 in https://github.com/microsoft/VPTQ/pull/66
* Update setup.py by YangWang92 in https://github.com/microsoft/VPTQ/pull/68
* refine online demo by YangWang92 in https://github.com/microsoft/VPTQ/pull/69
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/70
* Update setup.py by YangWang92 in https://github.com/microsoft/VPTQ/pull/72
* update device map by YangWang92 in https://github.com/microsoft/VPTQ/pull/74
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/80
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/81
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/82
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/83
* add math example by YangWang92 in https://github.com/microsoft/VPTQ/pull/84
* add acknowledgement and disclaimer by YangWang92 in https://github.com/microsoft/VPTQ/pull/85
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/94
* fix format by YangWang92 in https://github.com/microsoft/VPTQ/pull/95
* Use absolute imports by bndos in https://github.com/microsoft/VPTQ/pull/90
* Set __version__ by YangWang92 in https://github.com/microsoft/VPTQ/pull/97
* fix compiling error by YangWang92 in https://github.com/microsoft/VPTQ/pull/98
* Update vqlinear.py by laomao0 in https://github.com/microsoft/VPTQ/pull/103
* add package info by YangWang92 in https://github.com/microsoft/VPTQ/pull/104
* update pyproject by YangWang92 in https://github.com/microsoft/VPTQ/pull/106

New Contributors
* eltociear made their first contribution in https://github.com/microsoft/VPTQ/pull/47
* TITC made their first contribution in https://github.com/microsoft/VPTQ/pull/50
* bndos made their first contribution in https://github.com/microsoft/VPTQ/pull/90
* laomao0 made their first contribution in https://github.com/microsoft/VPTQ/pull/103

**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.2...v0.0.3

What's Changed
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/40
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/43
* add sm_89 by wejoncy in https://github.com/microsoft/VPTQ/pull/45
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/46
* add notebook by YangWang92 in https://github.com/microsoft/VPTQ/pull/48
* docs: update README.md by eltociear in https://github.com/microsoft/VPTQ/pull/47
* add catlog and index for readme by wejoncy in https://github.com/microsoft/VPTQ/pull/49
* support bf16 by wejoncy in https://github.com/microsoft/VPTQ/pull/51
* add gpu monitor at web app by TITC in https://github.com/microsoft/VPTQ/pull/50

New Contributors
* eltociear made their first contribution in https://github.com/microsoft/VPTQ/pull/47
* TITC made their first contribution in https://github.com/microsoft/VPTQ/pull/50

**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.2...v0.0.2.post1

What's Changed
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/22
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/25
* Patch 1 by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/27
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/28
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/30
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/31
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/32
* Update README.md by YangWang92 in https://github.com/microsoft/VPTQ/pull/33
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/34
* Update README.md by OpenSourceRonin in https://github.com/microsoft/VPTQ/pull/35
* add prompt args and check cuda kernel by YangWang92 in https://github.com/microsoft/VPTQ/pull/36
* update readme and tech report by YangWang92 in https://github.com/microsoft/VPTQ/pull/37
* support cuda-arch_list by wejoncy in https://github.com/microsoft/VPTQ/pull/38
* bump to 0.0.2 by wejoncy in https://github.com/microsoft/VPTQ/pull/39


**Full Changelog**: https://github.com/microsoft/VPTQ/compare/v0.0.1...v0.0.2