8 12

Jintao Zhang

jt-zhang

https://jt-zhang.github.io/

jtzhang-6

AI & ML interests

Efficient ML

Recent Activity

authored a paper 5 days ago

SageAttention2++: A More Efficient Implementation of SageAttention2

updated a collection 6 days ago

efficient ml

upvoted a paper 6 days ago

SageAttention2++: A More Efficient Implementation of SageAttention2

View all activity

Organizations

None yet

jt-zhang's activity

authored a paper 5 days ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published 7 days ago • 40

updated a collection 6 days ago

efficient ml

Collection

5 items • Updated 6 days ago

upvoted a paper 6 days ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published 7 days ago • 40

commented a paper 6 days ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published 7 days ago • 40 •

authored 2 papers 6 days ago

Accurate INT8 Training Through Dynamic Block-Level Fallback

Paper • 2503.08040 • Published Mar 11 • 1

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published 10 days ago • 38

upvoted 2 papers 6 days ago

Accurate INT8 Training Through Dynamic Block-Level Fallback

Paper • 2503.08040 • Published Mar 11 • 1

Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Paper • 2505.18875 • Published 10 days ago • 38

commented a paper 8 days ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published 18 days ago • 69 •

authored a paper 13 days ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published 18 days ago • 69

updated a collection 13 days ago

efficient ml

Collection

5 items • Updated 6 days ago

upvoted a paper 13 days ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published 18 days ago • 69

commented a paper 13 days ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published 18 days ago • 69 •

upvoted 2 papers 14 days ago

Faster Video Diffusion with Trainable Sparse Attention

Paper • 2505.13389 • Published 15 days ago • 35

Model Merging in Pre-training of Large Language Models

Paper • 2505.12082 • Published 17 days ago • 35

upvoted a paper 3 months ago

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published Mar 3 • 7

commented a paper 3 months ago

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published Mar 3 • 7 •

authored 2 papers 3 months ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published Feb 28 • 8

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published Mar 3 • 7