Glinthawk: A Two-Tiered Architecture for High-Throughput LLM Inference

Add code
Jan 20, 2025
Figure 1 for Glinthawk: A Two-Tiered Architecture for High-Throughput LLM Inference
Figure 2 for Glinthawk: A Two-Tiered Architecture for High-Throughput LLM Inference
Figure 3 for Glinthawk: A Two-Tiered Architecture for High-Throughput LLM Inference
Figure 4 for Glinthawk: A Two-Tiered Architecture for High-Throughput LLM Inference

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: