@raydistributed: Ray Serve LLM now offers 4.4x higher request throughput on prefill-heavy workloads, and 24.8x higher request throughput…

X AI KOLs Following Tools

Summary

Ray Serve LLM achieves 4.4x and 24.8x throughput improvements on prefill- and decode-heavy workloads via direct streaming, a new vLLM V2 executor backend, and HAProxy ingress, now available in Ray 2.56 in partnership with Google Cloud and vLLM.

Ray Serve LLM now offers 4.4x higher request throughput on prefill-heavy workloads, and 24.8x higher request throughput on decode-heavy workloads! Three major optimizations: - Direct streaming, bypassing an intermediate Ray Serve deployment on the response path with a new, control plane-only endpoint picker - A new, Ray V2 executor backend in vLLM, enabling optimizations such as async scheduling - HAProxy ingress, for ingress request routing at the speed of C All available in Ray 2.56. This is awesome work with @googlecloud and @vllm_project!
Original Article
View Cached Full Text

Cached at: 06/18/26, 10:11 PM

Ray Serve LLM now offers 4.4x higher request throughput on prefill-heavy workloads, and 24.8x higher request throughput on decode-heavy workloads!

Three major optimizations:

  • Direct streaming, bypassing an intermediate Ray Serve deployment on the response path with a new, control plane-only endpoint picker
  • A new, Ray V2 executor backend in vLLM, enabling optimizations such as async scheduling
  • HAProxy ingress, for ingress request routing at the speed of C

All available in Ray 2.56. This is awesome work with @googlecloud and @vllm_project!

Seiji Eicher (@seiji_________): 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

Similar Articles

@robertnishihara: Try Ray 2.56!

X AI KOLs Following

Ray 2.56 is released with stability improvements for Ray Data and a re-architecture of Ray Serve for better LLM serving performance.