Picture for Daiyaan Arfeen

Daiyaan Arfeen

GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism

Add code
Jun 24, 2024
Viaarxiv icon

SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification

Add code
May 16, 2023
Figure 1 for SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
Figure 2 for SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
Figure 3 for SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
Figure 4 for SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
Viaarxiv icon

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks

Add code
Nov 10, 2019
Figure 1 for HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Figure 2 for HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Figure 3 for HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Figure 4 for HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
Viaarxiv icon

Unsupervised Projection Networks for Generative Adversarial Networks

Add code
Oct 06, 2019
Figure 1 for Unsupervised Projection Networks for Generative Adversarial Networks
Figure 2 for Unsupervised Projection Networks for Generative Adversarial Networks
Figure 3 for Unsupervised Projection Networks for Generative Adversarial Networks
Figure 4 for Unsupervised Projection Networks for Generative Adversarial Networks
Viaarxiv icon