Episode Details
Back to EpisodesPrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving
Published 2 weeks, 6 days ago
Description
## Episode Summary
In this episode, we cover:
- **PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving** (arXiv)
- **Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation** (arXiv)
- **Checking In On The ISA Wars And Its Impact On CPU Architectures - Hackaday** (google_arch)
- **Kari Hepola: Custom tools make RISC-V processors faster and easier to design - tuni.fi** (google_riscv)
- **Enabling Comprehensive CWE-based Assurance for RISC-V Processors - semiengineering.com** (google_riscv)
---
*Sponsored by Ada, Ago Consulting, and Zen Semiconductor*