Suvrakamal Das

subhrokomol's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in mistralai/Mistral-7B-Instruct-v0.2 about 2 months ago

deepspeed inference tensor parallelism memory footprint doesn't decrease with deepspeed tp_size increase.

6

#92 opened 7 months ago by jiangtaozh