Adrian L

alancucki's activity

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

updated a model 23 days ago

nvidia/Qwen3-8B-DMS-8x

Updated 23 days ago • 1.93k • 34

published a model 25 days ago

nvidia/Qwen3-8B-DMS-8x

Updated 23 days ago • 1.93k • 34

upvoted a paper 8 months ago

Inference-Time Hyper-Scaling with KV Cache Compression

Paper • 2506.05345 • Published Jun 5, 2025 • 28

updated a collection about 1 year ago

DMC

Collection

LLMs equipped with Dynamic Memory Compression to accelerate generation. • 4 items • Updated 9 days ago • 4

updated 8 models about 1 year ago

nvidia/Llama-2-13B-DMC-4x

Updated Dec 22, 2024 • 1

nvidia/Llama-2-13B-DMC-8x

Updated Dec 22, 2024 • 2

nvidia/Llama-2-7B-DMC-8x

Updated Dec 22, 2024 • 2

nvidia/Llama-2-7B-DMC-4x

Updated Dec 22, 2024 • 2

nvidia/Llama-2-7B-DMC-4x

Updated Dec 22, 2024 • 2

nvidia/Llama-2-13B-DMC-8x

Updated Dec 22, 2024 • 2

nvidia/Llama-2-13B-DMC-4x

Updated Dec 22, 2024 • 1

nvidia/Llama-2-7B-DMC-8x

Updated Dec 22, 2024 • 2