Jintao Zhang

jt-zhang's activity

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

New activity in jt-zhang/SageAttention3 29 days ago

Any improvement on Ada Lovelace (RTX 4xxx) ?

👀 1

1

#1 opened 29 days ago by

NielsGx

New activity in jt-zhang/SageAttention2_plus about 1 month ago

The performance of sageattention2.2 is worse than sageattention2.1.

5

#7 opened about 2 months ago by

triplemu

New activity in jt-zhang/SageAttention2_plus about 2 months ago

5090

1

#6 opened about 2 months ago by

xiaomingxu1995

In the latest commit, we set the default sageattn API to SageAttn2++

🚀 ❤️ 2

#5 opened about 2 months ago by

jt-zhang

SageAttention2++ needs CUDA 12.8

🔥 1

1

#3 opened about 2 months ago by

jt-zhang

commented 2 papers about 2 months ago

Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures

Paper • 2505.09343 • Published May 14 • 68 •

5

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published May 27 • 47 •

3

commented 3 papers 3 months ago

SageAttention2++: A More Efficient Implementation of SageAttention2

Paper • 2505.21136 • Published May 27 • 47 •

3

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

Paper • 2505.11594 • Published May 16 • 76 •

8

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

Paper • 2505.11594 • Published May 16 • 76 •

8

commented a paper 5 months ago

SAGE: A Framework of Precise Retrieval for RAG

Paper • 2503.01713 • Published Mar 3 • 7 •

2

commented 2 papers 6 months ago

Identifying Sensitive Weights via Post-quantization Integral

Paper • 2503.01901 • Published Feb 28 • 8 •

2

SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference

Paper • 2502.18137 • Published Feb 25 • 58 •

2

commented 4 papers 8 months ago

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

Paper • 2412.14711 • Published Dec 19, 2024 • 16 •

2

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 56 •

9

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 56 •

9

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 56 •

9

commented 2 papers 9 months ago

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 56 •

9

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

Paper • 2411.10958 • Published Nov 17, 2024 • 56 •

9

commented a paper 11 months ago

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

Paper • 2410.02367 • Published Oct 3, 2024 • 51 •

5