zijie tian
zijie-tian
AI & ML interests
Storage for AI
Recent Activity
upvoted
a
paper
about 16 hours ago
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
upvoted
an
article
11 days ago
MInference 1.0: 10x Faster Million Context Inference with a Single GPU
upvoted
an
article
4 months ago
Unlocking Longer Generation with Key-Value Cache Quantization
Organizations
