zijie tian
zijie-tian
AI & ML interests
Storage for AI
Recent Activity
liked
a model
1 day ago
Qwen/Qwen3.5-397B-A17B
upvoted
a
paper
about 2 months ago
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
upvoted
a
paper
2 months ago
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Organizations
