SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Add code
Apr 07, 2024
Figure 1 for SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
Figure 2 for SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
Figure 3 for SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget
Figure 4 for SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: