4 papers indexed here
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.
COPE (Composable Offloading Policy Emulator), which selects the best-performing MoE offloading policy for a target model-platform configuration before runtime integration, and reduces policy-specific implementation effort by up to 74%.
Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the highly dynamic nature of LLM workloads requires providers to continuously adjust serving capacity to match fluctuating demand. Scaling MoE serving cannot be efficiently...
This work analyzes 118,000 skills and proposes SkillVM, a compilation and runtime system designed for portable and efficient skill execution that achieves up to 3.2× speedup with enhanced parallelism, and 19-50× latency reduction through code solidification.
WaferAI-SIM enables simulator-driven co-design of LLM serving strategies and multi-core accelerator architectures, targeting the early design stage in which emerging platforms are not yet broadly available for empirical serving studies, and provides guidance for co-designing hardware architectures and serving strategie...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
