kumar

kapil1611's activity

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

New activity in google/flan-t5-xxl about 1 year ago

Why 4bit quantised is slower than fp16

2

#63 opened about 1 year ago by kapil1611

New activity in google/flan-t5-large about 1 year ago

Why 4bit quantised performance is slower than fp 16?

2

#17 opened about 1 year ago by kapil1611