Charles Frye

mentions 2 type Person feed RSS

// recent coverage 2 mentions

19:06

2026-06-25

modal.com

ai-infrastructure

Routing for serverless servers with Pingora, Envoy, and Spanner

Modal introduced Servers, a new ultra-low-latency HTTP serving solution for serverless applications, built on Pingora, Envoy, and Spanner. The system minimizes overhead by avoiding control-plane looku…

23:22

2026-06-11

modal.com

large-language-models

Making FlashAttention-4 faster for inference

Modal AI engineers Charles Frye and David Wang optimized FlashAttention-4 for large language model inference, focusing on decode-heavy workloads dominated by memory bandwidth-limited token generation.…

// co-occurs with top 8 entities

FlashAttention-4 1 David Wang 1 Together AI 1 Modal 1 Pingora 1 Envoy 1 Spanner 1 Richard Gong 1

// topics top 6 topics

large language models 2 ai infrastructure 2 ai research 1 machine learning 1 ai chips 1 ai products 1