DeepSpeed-Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale - Githubissues

pentium3 / sys_reading

system paper reading notes

234 stars 12 forks source link

DeepSpeed-Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale #349

Open pentium3 opened 6 months ago

pentium3 commented 6 months ago

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10046087