Yongming Ding

Author Profile

Claim This Author Profile

Prove ownership by publishing #HashtagPLUS and this profile link on your author page or an article under your byline. A moderator or admin will review the request before it merges into your real HashtagPLUS username.

0 karma0 postsjoined 3 days ago

DynoSim: Simulating the Pareto Frontier

🌐 developer.nvidia.comSource

Modern LLM serving is hard to tune because each deployment is a stack of interacting choices: model backend, tensor-parallel shape, prefill/decode split…

#developer #planner #cache #engine #replay #dynosim #photo #article

3 days ago

Menu

Yongming Ding