Picture for Zhenhua Han

Zhenhua Han

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Add code
Jul 02, 2024
Viaarxiv icon

Parrot: Efficient Serving of LLM-based Applications with Semantic Variable

Add code
May 30, 2024
Viaarxiv icon

Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models

Add code
Jun 01, 2023
Figure 1 for Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Figure 2 for Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Figure 3 for Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Figure 4 for Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Viaarxiv icon

Online Video Streaming Super-Resolution with Adaptive Look-Up Table Fusion

Add code
Mar 01, 2023
Figure 1 for Online Video Streaming Super-Resolution with Adaptive Look-Up Table Fusion
Figure 2 for Online Video Streaming Super-Resolution with Adaptive Look-Up Table Fusion
Figure 3 for Online Video Streaming Super-Resolution with Adaptive Look-Up Table Fusion
Figure 4 for Online Video Streaming Super-Resolution with Adaptive Look-Up Table Fusion
Viaarxiv icon

SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation

Add code
Jan 26, 2023
Figure 1 for SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation
Figure 2 for SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation
Figure 3 for SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation
Figure 4 for SparDA: Accelerating Dynamic Sparse Deep Neural Networks via Sparse-Dense Transformation
Viaarxiv icon