Autoawq

Latest version: v0.2.8

Safety actively analyzes 714772 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 5

0.2.8

What's Changed
* Minimum of torch 2.2.0 during build by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/649
* post release 1 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/650
* Post release 2 - All additional packages goes into extras by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/653
* Fused attention: Switch to Flash Decoding by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/656
* Add EXAONE support by lgai-exaone in https://github.com/casper-hansen/AutoAWQ/pull/651
* fix exaone import by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/659
* fix "Expected all tensors to be on the same device" by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/664
* multi-gpu fix by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/668
* Fix missing embed_tokens by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/671
* install hub main branch by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/672
* pin huggingface_hub by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/673
* bump to 0.2.7.post3 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/674
* improve type hinting and fix use_cache by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/680
* fix bug when using FSDP by kaixuanliu in https://github.com/casper-hansen/AutoAWQ/pull/696
* Added DeepSeek V3 support. by LagPixelLOL in https://github.com/casper-hansen/AutoAWQ/pull/688
* add ability to define torch_dtype by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/697
* automatically load dtype from config by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/698
* Enable triton on XPU devices by Egor-Krivov in https://github.com/casper-hansen/AutoAWQ/pull/695
* fix workflow build by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/699
* bump to 028 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/700

New Contributors
* lgai-exaone made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/651
* kaixuanliu made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/696
* LagPixelLOL made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/688
* Egor-Krivov made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/695

**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.7...v0.2.8

0.2.7.post3

What's Changed
* Fused attention: Switch to Flash Decoding by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/656
* Add EXAONE support by lgai-exaone in https://github.com/casper-hansen/AutoAWQ/pull/651
* fix exaone import by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/659
* fix "Expected all tensors to be on the same device" by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/664
* multi-gpu fix by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/668
* Fix missing embed_tokens by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/671
* install hub main branch by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/672
* pin huggingface_hub by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/673
* bump to 0.2.7.post3 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/674

New Contributors
* lgai-exaone made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/651

**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.7.post2...v0.2.7.post3

0.2.7.post2

What's Changed
* Post release 2 - All additional packages goes into extras by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/653


**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.7.post1...v0.2.7.post2

0.2.7.post1

What's Changed
* Minimum of torch 2.2.0 during build by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/649
* post release 1 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/650


**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.7...v0.2.7.post1

0.2.7

What's Changed
* fix: pass rope_theta argument when initializing LlamaLikeBlock for models like qwen2, mistral, etc. by Shuai-Xie in https://github.com/casper-hansen/AutoAWQ/pull/568
* Add Gemma2 support. by radi-cho in https://github.com/casper-hansen/AutoAWQ/pull/562
* ignore onnx in ignore_patterns by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/570
* Add Internlm2 support by Crystalcareai in https://github.com/casper-hansen/AutoAWQ/pull/576
* quantization fails with old `datasets` by stas00 in https://github.com/casper-hansen/AutoAWQ/pull/593
* doc: replace a broken example with a working one by stas00 in https://github.com/casper-hansen/AutoAWQ/pull/595
* Implement NO_KERNELS flag and update torch requirement by devin-ai-integration in https://github.com/casper-hansen/AutoAWQ/pull/582
* AWQ Triton kernels. Make `autoawq-kernels` optional. by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/608
* device_map defaults to auto by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/607
* Let installed PyTorch decide required version number by wasertech in https://github.com/casper-hansen/AutoAWQ/pull/573
* Replace itrex qbits to ipex woq linear by jiqing-feng in https://github.com/casper-hansen/AutoAWQ/pull/549
* enable awq ipex linear in transformers by jiqing-feng in https://github.com/casper-hansen/AutoAWQ/pull/610
* fix for "two devices" issue due to RoPE changes by davedgd in https://github.com/casper-hansen/AutoAWQ/pull/630
* add qwen2vl support by kq-chen in https://github.com/casper-hansen/AutoAWQ/pull/599
* Add support for Phi-3-vision series model by Isotr0py in https://github.com/casper-hansen/AutoAWQ/pull/596
* support minicpm3.0 by LDLINGLINGLING in https://github.com/casper-hansen/AutoAWQ/pull/605
* Enable Intel GPU path and lora finetune and change examples to support different devices by jiqing-feng in https://github.com/casper-hansen/AutoAWQ/pull/631
* Replace custom sharding with save_torch_state_dict from huggingface_hub by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/644
* New release (0.2.7) + Fix build by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/647
* Only build once by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/648

New Contributors
* Shuai-Xie made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/568
* radi-cho made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/562
* Crystalcareai made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/576
* stas00 made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/593
* wasertech made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/573
* jiqing-feng made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/549
* davedgd made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/630
* kq-chen made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/599

**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.6...v0.2.7

0.2.6

What's Changed
* Cohere Support by TechxGenus in https://github.com/casper-hansen/AutoAWQ/pull/457
* Add phi3 support by pprp in https://github.com/casper-hansen/AutoAWQ/pull/481
* Support Weight-Only quantization on CPU device with QBits backend by PenghuiCheng in https://github.com/casper-hansen/AutoAWQ/pull/437
* Fix typo by wanyaworld in https://github.com/casper-hansen/AutoAWQ/pull/486
* Add updates + sponsorship by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/495
* Update README.md by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/497
* Update doc by imba-tjd in https://github.com/casper-hansen/AutoAWQ/pull/499
* add support for Openbmb/MiniCPM by LDLINGLINGLING in https://github.com/casper-hansen/AutoAWQ/pull/504
* Update RunPod support by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/514
* add deepseek v2 support by TechxGenus in https://github.com/casper-hansen/AutoAWQ/pull/508
* nan problem of Qwen2-72B quantization by baoyf4244 in https://github.com/casper-hansen/AutoAWQ/pull/519
* Qwen nan fix by baoyf4244 in https://github.com/casper-hansen/AutoAWQ/pull/522
* fix deepseek v2 input feat by TechxGenus in https://github.com/casper-hansen/AutoAWQ/pull/524
* Batched quantization by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/516
* Fix step size when computing clipping by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/531
* Pin torch version to 2.3.1 by devin-ai-integration in https://github.com/casper-hansen/AutoAWQ/pull/542
* Revert "Pin torch version to 2.3.1 (542)" by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/547
* CLI example + Runpod launch script by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/548
* Print warning if AutoAWQ cannot load extensions by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/515
* Remove progress bars by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/550
* Add test for chunked methods by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/551
* Llama with inputs_embeds only(LLava-v1.5 bug fixed) and Llava-v1.6 Support by WanBenLe in https://github.com/casper-hansen/AutoAWQ/pull/471
* Better CLI + RunPod Script by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/552
* Release 026 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/546
* pin torch==2.3.1 by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/554
* Remove ROCm build and only build for PyPi by casper-hansen in https://github.com/casper-hansen/AutoAWQ/pull/555

New Contributors
* pprp made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/481
* PenghuiCheng made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/437
* wanyaworld made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/486
* imba-tjd made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/499
* LDLINGLINGLING made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/504
* baoyf4244 made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/519
* devin-ai-integration made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/542
* WanBenLe made their first contribution in https://github.com/casper-hansen/AutoAWQ/pull/471

**Full Changelog**: https://github.com/casper-hansen/AutoAWQ/compare/v0.2.5...v0.2.6

Page 1 of 5

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.