Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
YangWang92 created a comment on a pull request on huggingface/transformers
> Super sorry for the late review, I am a bit under water 😓 Thanks so much! And thanks to everyone for their help! Special thanks to @xianbaoqian for the support—super grateful! 😊
YangWang92 opened an issue on lzd19981105/quip-sharp-qwenvl
Could you provide the measurement results in text format?
Thank you for your contribution. Could you provide the measurement results in text format? I saw the radar chart, but I couldn't find the text data. We are also using VPTQ for quantizing VLMs, and ...
YangWang92 created a comment on an issue on microsoft/VPTQ
> > Hi [@caronzh03](https://github.com/caronzh03), > > We are currently using the Hessian matrix collection from https://github.com/Cornell-RelaxML/quip-sharp?tab=readme-ov-file#quantization. Pleas...
YangWang92 pushed 18 commits to algorithm YangWang92/VPTQ
- Set __version__ (#97) 7bb2d01
- fix compiling error (#98) fix compiling error fde03de
- Update vqlinear.py (#103) fix index unpack size ace1393
- add package info (#104) add package info 63d1bc1
- update pyproject (#106) 46ad33b
- Update README.md (#108) Update README.md, add pypi e7746ba
- Update README.md (#109) fix command typo 7d561c2
- Add CUDA_HOME instructions to README (#112) Co-authored-by: Yang Wang <[email protected]> 05820d6
- Update README.md (#117) 3ff720b
- fix config format for transformers (#120) f49341e
- Bump to 0.0.4 (#121) c5d86da
- fix version__ (#122) 27b70af
- fix setup version number (#123) 4adafff
- Update model_base.py (#124) fix quantization config for layers 139a380
- Update README.md (#127) update roadmap ac7258f
- Update README.md (#129) 662a5c3
- Update vptq_example.ipynb (#138) fix vptq install in ipynb 171af83
- Merge branch 'main' into algorithm 7703791
YangWang92 pushed 4 commits to algorithm YangWang92/VPTQ
- update version (#99) update version 8a1074a
- update version (#100) update version b246a3d
- update algorithm (#105) update algorithm --------- Co-authored-by: laomao0 <[email protected]... 12b03f5
- Adds nvembed model to quantization algorithm (#139) Add support for quantizing the NV-Embed model using VPTQ. Benchm... 441196f
YangWang92 pushed 3 commits to main YangWang92/VPTQ
YangWang92 created a comment on a pull request on huggingface/transformers
Hi @ArthurZucker, Just a polite ping to check in—may I ask if there’s anything else we need to modify? Thank you! Best regards, Yang
YangWang92 created a comment on an issue on ROCm/ROCm
I encountered a similar issue with the Mi300x, where flash_attention + vLLM triggers a problem. ``` [5615152.198602] gmc_v9_0_process_interrupt: 6 callbacks suppressed [5615152.198606] amdgpu 00...