Balsamo Gabriele

Gabrobals's activity

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

New activity in nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 4 months ago

[Research] Adaptive-K Routing Validation: 33% Compute Savings on Nemotron 3 Nano

❤️ 3

#41 opened 4 months ago by

Gabrobals

New activity in Qwen/Qwen1.5-MoE-A2.7B 4 months ago

Adaptive-K Routing: 32% compute savings for Qwen-MoE

1

#8 opened 4 months ago by

Gabrobals

New activity in mistralai/Mixtral-8x7B-v0.1 4 months ago

Adaptive-K Routing: 52% compute savings with dynamic expert selection

1

#70 opened 4 months ago by

Gabrobals

Adaptive-K Routing: 52% compute savings with dynamic expert selection

1

#70 opened 4 months ago by

Gabrobals