Episode Details

Back to Episodes

CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

Published 3 months, 1 week ago
Description
## Episode Summary In this episode, we cover: - **CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation** (arXiv) - **Phase Matters: Characterizing Heterogeneous Vision-Language Inference on a Mobile SoC** (arXiv) - **AI is stress-testing processor architectures and RISC-V fits the moment - EDN - Voice of the Engineer** (google_riscv) - **Milk-V Jupiter2 is mini PC with a SpacemiT K3 RISC-V processor - Liliputing** (google_riscv) - **SpacemiT to launch server-class RISC-V processor following capital injection - South China Morning Post** (google_riscv) --- *Sponsored by LimitLess AI*
Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us