Sihan Chen

Hi @marcosnils @williamquiviger! I and @Chen-Zidi would like to kindly ask you for a check and maybe a merge because we have tried over the Internet and there are no...

@marcosnils Thx ~

@v1d3rm3 , maybe you can refer to cygwin and choco installation of `make` command on windows

@raj-ritu17 you only need to pass `model_type='llama'` and you do not need to pass the `model_name` here based on the API. Please try this ``` model.init_from_bin(model_type="llama", model_path="runtime_outs/ne_llama_q_int4_bestla_cfp32_g32.bin") ``` Still get...

@raj-ritu17 @Zhenzhong1 , with few updates this should work https://github.com/intel/intel-extension-for-transformers/blob/update_talkingbot_pc/intel_extension_for_transformers/neural_chat/examples/deployment/talkingbot/pc/build_talkingbot_on_pc.ipynb

Hi @AIhasArrived , AWS SPR map to `m7i.48xlarge`.

@AIhasArrived , > If a borrowed this CPU, do you think I could use it to run MULTIPLE "xtalker" processes at once? sure you can. xtalker basically bind different cores...

Hi @BbChip0103 , Compared to the Colab demo that using a Tesla T4 from the original SadTalker, xtalker is 6~8 times faster in rendering on one Intel Xeon Sapphire Rapids...

it depends on your hardware. You can increase from 2,4,8,16... to see which case has better performance

No, it cannot. The parallelism is only for Xeon CPU.