Episode Details

Back to Episodes

Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-In-Memory Systems

Published 2 months, 1 week ago
Description
## Episode Summary In this episode, we cover: - **Selective KV Cache Protection for Noise-Resilient LLM Inference on Analog Compute-In-Memory Systems** (arXiv) - **WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization** (arXiv) - **Evaluating and Calibrating Performance On RISC-V Vector Processors (KTH, LLNL, BSC) - Semiconductor Engineering** (google_riscv) - **RISC-V Mentorship Taught Me the RISC-V ISA Is Far More Than a Reference Manual** (riscv_news) - **Zhihe A210 octa-core RISC-V SoC with 12 TOPS NPU powers SoM-based development board - cnx-software.com** (google_riscv) --- *Sponsored by Ada, Ago Consulting, and Zen Semiconductor*
Listen Now

Love PodBriefly?

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

Support Us