TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 117
Sunho Kim
sunhokim
·
AI & ML interests
None yet
Recent Activity
liked a model 6 days ago
zai-org/GLM-5.3 upvoted a paper 5 months ago
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression liked a model 5 months ago
nvidia/Gemma-4-31B-IT-NVFP4Organizations
upvoted a paper 5 months ago
upvoted an article 9 months ago
Article
Gotchas in Tokenizer Behavior Every Developer Should Know
qgallouedec
• • 72 upvoted an article 11 months ago
Article
A Review on the Evolvement of Load Balancing Strategy in MoE LLMs: Pitfalls and Lessons
NormalUhr
• • 38