We have 3 of 19 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
VIPER is presented, a unified, lightweight, and architecture-aware performance evaluation framework for PIM DSE, providing rapid architecture-aware performance estimates for iterative DSE without repeated cycle-accurate simulation.
DynaNDE is presented, a dynamic near-data expert scheduling framework that exploits NPU-NDP collaboration to accelerate batched MoE inference and introduces an analytical performance model that captures hardware heterogeneity, data-movement costs, and communication-computation overlap in cooperative NPU-NDP execution.
With rising popularity of LLMs, the performance, scalability, and resource-efficiency of inferences become a crucial challenge. The core part of the inference process is the KV cache, which avoids recomputing intermediate attention states, and the batching strategy that batches multiple requests per forward pass to lev...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
