Seiji Eicher

@seiji_________

Ray + vLLM = 💘 @ Anyscale | Prev: @Stanford, @Apple

San Francisco, CA

Joined June 2025

Pinned
Seiji Eicher
@seiji_________
Jun 18
Today we are excited to announce, in partnership with the GKE team at Google Cloud (@googlecloud), a major milestone in Ray Serve LLM’s production serving capability. Ray Serve LLM now matches high performance, rust-based routing frameworks such as vllm-router (@vllm_project) in
Seiji Eicher
@seiji_________
Aug 7
sf culture is no one knowing how balcony seating at the amc kabuki works
Seiji Eicher
@seiji_________
Aug 1
an early role for Leopold Aschenbrenner in north by northwest (1959)
Seiji Eicher
@seiji_________
Aug 1
spotted: pikachu DeepSeek rivian (280-S) which one of you was this
Seiji Eicher
@seiji_________
Jun 24
Ray Serve LLM + vLLM + Google Cloud = high performance LLM inference :) Was great collaborating on our newest optimizations w/ @GoogleCloudTech!
Google Cloud Tech
@GoogleCloudTech
Jun 23
Through our partnership with @anyscalecompute, Ray Serve LLM on Google Kubernetes Engine now offers 5x higher throughput and 8x lower latency for distributed inference! Read more about scaling inference without the bottlenecks → goo.gle/4w50CXB