Gptqmodel

What's Changed
* 🚀 [FEATURE] Added Transformers Integration via monkeypatch by ZX-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/147
* 👾 [FIX] Typo causing Gemma 2 errors by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/158


**Full Changelog**: https://github.com/ModelCloud/GPTQModel/compare/v0.9.3...v0.9.4

What's Changed
* 🚀 [MODEL] Add Gemma 2 support by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/131
* 🚀 [OTHER] Calculate ppl on gpu by ZYC-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/135
* ✨ [REFRACTOR] BaseQuantLinear and avoid using shared QuantLinear cls name by PZS-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/116
* ✨ [KERNEL] Bitblas cache stablity by Qubitium in https://github.com/ModelCloud/GPTQModel/pull/129
* 👾 [FIX] Export TORCH_CUDA_ARCH_LIST in install.sh by LeiWang1999 in https://github.com/ModelCloud/GPTQModel/pull/133
* 👾 [FIX] Limit Bitblas numexpr thread usage by Qubitium in https://github.com/ModelCloud/GPTQModel/pull/125
* 👾 [FIX] Revert "Skip opt fc1/fc2 for quantization" due to inference regressions (118)" by Qubitium in https://github.com/ModelCloud/GPTQModel/pull/149
* ✨ [REFRACTOR] remove max_memory arg by CL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/144
* 🤖 [CI] Fix test was skipped by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/145
* 🤖 [CI] Add GPU selector for runner by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/148

New Contributors
* LeiWang1999 made their first contribution in https://github.com/ModelCloud/GPTQModel/pull/133

**Full Changelog**: https://github.com/ModelCloud/GPTQModel/compare/v0.9.2...v0.9.3

What's Changed

Added auto-padding of model in/out-features for exllama and exllama v2. Fixed quantization of OPT and DeepSeek V2-Lite models. Fixed inference for DeepSeek V2-Lite.

* ✨ [FEATURE/FIX] Padding infeatures/outfeatures for exllama, exllama v2, and marlin by Qubitium LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/98
* ✨ [REFRACTOR] remove use_cuda_fp16 argument by ZX-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/97
* ✨ [REFRACTOR] `model.post_init` by PZS-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/103
* ✨ [BUILD] Add UV PIP usage instructions information by CL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/114
* 👾 [FIX] DeepSeek-V2-Lite load by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/112
* 👾 [FIX] Opt fc1/fc2 layer modules should not be quantized by Qubitium in https://github.com/ModelCloud/GPTQModel/pull/118

New Contributors
* CL-ModelCloud made their first contribution in https://github.com/ModelCloud/GPTQModel/pull/114

**Full Changelog**: https://github.com/ModelCloud/GPTQModel/compare/v0.9.1...v0.9.2

* ✨ [FEATURE + New FORMAT] Add Bitblas Format/Kernel Support by LeiWang1999 ZX-ModelCloud Qubitium in https://github.com/ModelCloud/GPTQModel/pull/39
* ✨ [FEATURE] Save sharded by LaaZa CSY-ModelCloud PZS-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/40 https://github.com/ModelCloud/GPTQModel/pull/69
* ✨ [FEATURE/SECURITY] Add `verify_hash` to validate model weights via stored hashes by PZS-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/50
* 🚀 [CORE/REFACTOR] Consolidate 6+ passive `use_xxx` and `disable_xxx` args to single explicit `backend` arg by ZX-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/68
* 🚀 [MODEL] DeepSeek-V2 support by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/51
* 🚀 [MODEL] DeepSeek-V2-Lite support by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/74
* 🚀 [MODEL] DBRX Converted support by Qubitium LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/38
* 👾 [FIX] Batching of calibration data in .quantize() by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/70
* 👾 [FIX] Cannot pickle 'module' object for 8 bit (fix 47) by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/49
* 👾 [FIX] Format load check by Qubitium in https://github.com/ModelCloud/GPTQModel/pull/53
* 👾 [FIX] `save_quantized()` using wrong model to obtain state_dict() by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/54
* 👾 [FIX] Rename exllama_kernels class name to fix import/ext conflicts with autogptq by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/71
* 🤖 [CI] Speed up unit tests CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/37 and https://github.com/ModelCloud/GPTQModel/pull/41 and https://github.com/ModelCloud/GPTQModel/pull/46 and https://github.com/ModelCloud/GPTQModel/pull/55
* 🤖 [CI] Improve unit tests ZYC-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/58 https://github.com/ModelCloud/GPTQModel/pull/72
* 🤖 👾 [CI] FIx Marlin format `desc_act` must be False. by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/57


New Contributors
* LeiWang1999 in https://github.com/ModelCloud/GPTQModel/pull/39
* LaaZa in https://github.com/ModelCloud/GPTQModel/pull/40
* PZS-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/50
* ZYC-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/58

**Full Changelog**: https://github.com/ModelCloud/GPTQModel/compare/v0.9.0...v0.9.1

What's Changed (First Release since AutoGPTQ fork)

4 New Models plus `sym=False` asymmetry and `lm_head` quantized inference support.

* ✨ [FEATURE/BUG] `sym=false` support by qwopqwop200, Qubitium, fxmarty
* ✨ [FEATURE] `lm_head` quantization inference by Qubitium
* 🚀 [MODEL] ChatGLM by LRL-ModelCloud Qubitium
* 🚀 [MODEL] MiniCPM model support by LDLINGLINGLING, Qubitium in https://github.com/ModelCloud/GPTQModel/pull/18
* 🚀 [MODEL] Phi-3 model support by davidgxue, ZX-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/27
* 🚀 [MODEL] QwenMoE model support by bozheng-hit, LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/24
* 🚀 [CORE] Faster quantization and better quality (PPL) quant by Qubitium
* 👾[BUG] H100 crash by Qubitium
* 👾[BUG] Packing perf regression on high core-count systems by Qubitium
* 🚀 [REFRACTOR] Major refractor and code debloat by Qubitium
* 🤖 [CI] Code quality by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/31
* 🤖 [CI] Add Perplexity regression test by LRL-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/1
* 🤖 [CI] Add Runner by CSY-ModelCloud in https://github.com/ModelCloud/GPTQModel/pull/3

**Full Changelog**: https://github.com/ModelCloud/GPTQModel/commits/v0.9.0