Open muhammad-asn opened 9 months ago
We are currently working on support for HPU hardware on the training side of DeepSpeed. I expect we will also work towards supporting it for inference as well, but we do not have any set goals/deadlines around that support at this time.
@mrwyattii thanks
Currently the TGI have tgi-gaudi to support the HPU for Gaudi 2 and also VLLM is included their roadmap in Q1 2024
Is the DeepSpeed-MII will support habana (HPU) hardware as well?
Thank you