James Neville

Khawn2u's activity

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

upvoted a collection about 2 months ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 18 days ago • 78

upvoted a collection 8 months ago

Qwen3

Collection

84 items • Updated 7 days ago • 1.54k

upvoted a collection 9 months ago

Nemotron-UltraLong

Collection

3 items • Updated 14 days ago • 19

upvoted an article 10 months ago

view article

Article

MLA: Redefining KV-Cache Through Low-Rank Projections and On-Demand Decompression

• 

Feb 4, 2025

•

18

upvoted 3 papers 10 months ago

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

Paper • 2412.02252 • Published Dec 3, 2024 • 2

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published Feb 11, 2025 • 57

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22, 2025 • 126

upvoted an article 11 months ago

view article

Article

Open-source DeepResearch – Freeing our search agents

• 
• 
• +3

Feb 4, 2025

•

1.31k

upvoted a collection 11 months ago

Hibiki fr-en

Collection

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 7 items • Updated 14 days ago • 55