Jeff Rasley

jeffra's activity

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

updated a collection about 16 hours ago

SwiftKV Models

Collection

SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation. • 4 items • Updated about 16 hours ago • 5

updated 3 models about 2 months ago

Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8

Updated Dec 13, 2024 • 78

Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8

Updated Dec 13, 2024 • 78

Snowflake/Llama-3.1-SwiftKV-405B-Instruct-FP8

Updated Dec 13, 2024 • 78