Recent Posts

• Accelerating LLM Inference with Parallel Draft Models (PARD)
  by dhruvdhon 4/11/2025, 6:10:02 PM with 0 comments
• Open-sourcing Three EXAONE 3.5 Models: 2.4B, 7.8B, 32B
  by dhruvdhon 12/9/2024, 3:55:24 PM with 5 comments
• The Tyranny of Possibilities in the Design of Task-Oriented LLM Systems
  by dhruvdhon 1/2/2024, 1:05:22 PM with 2 comments