---
type: "post"
id: "vllm-blog-serving-deepseek-v4-1-flash-at-073f14"
slug: "vllm-blog-serving-deepseek-v4-1-flash-at-073f14"
title: "vLLM blog: Serving DeepSeek-V4.1-Flash at scale, matching DeepInfer and scaling to GB300 NVL72"
description: "Inferact and the vLLM team published a performance study on October 23, 2026, covering online serving of DeepSeek-V4.1-Flash on a single NVIDIA GB300 NVL72 rack."
retrieval_nugget: "Inferact and the vLLM team published a performance study on October 23, 2026, covering online serving of DeepSeek-V4.1-Flash on a single NVIDIA GB300 NVL72 rack."
published_at: "2026-10-26"
updated_at: "2026-10-26"
record_date: "2026-10-26"
date_kind: "published_at"
topics: ["inference","ai-infrastructure","compute"]
entities: ["vLLM","DeepSeek-V4.1-Flash","DeepInfer","NVIDIA GB300 NVL72","SemiAnalysis AgentX","Inferact"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Serving DeepSeek-V4.1-Flash at Scale: vLLM Matches DeepInfer and Scales to GB300 NVL72 | vLLM Blog"
prior_refs: ["memory:96512f02-f285-8f7e-a3b8-6c2aab62c5f9","memory:4c416acd-47a0-818c-af99-bc98dd032139","memory:229dab74-a25f-8cfd-a488-19c0d853b42b"]
source_url: "https://blog.vllm.ai/blog/2026-10-23-deepseek-v41-flash-pd-wide-ep"
source_urls: ["https://blog.vllm.ai/blog/2026-10-23-deepseek-v41-flash-pd-wide-ep"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:vllm-blog-serving-deepseek-v4-1-flash-at-073f14"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/vllm-blog-serving-deepseek-v4-1-flash-at-073f14/","markdown":"https://newruntime.com/posts/vllm-blog-serving-deepseek-v4-1-flash-at-073f14.md","json":"https://newruntime.com/posts/vllm-blog-serving-deepseek-v4-1-flash-at-073f14.json"}
---

# vLLM blog: Serving DeepSeek-V4.1-Flash at scale, matching DeepInfer and scaling to GB300 NVL72

## Retrieval answer

Inferact and the vLLM team published a performance study on October 23, 2026, covering online serving of DeepSeek-V4.1-Flash on a single NVIDIA GB300 NVL72 rack.

Inferact and the vLLM team published a performance study on October 23, 2026, covering online serving of DeepSeek-V4.1-Flash on a single NVIDIA GB300 NVL72 rack. The tested configuration combines prefill/decode disaggregation with Wide-EP expert parallelism.

On the SemiAnalysis AgentX workload, vLLM reports 954,000 tokens per second per GPU and a P90 rate of 196 tokens per second per user. That is 7.9 times the team's earlier single-node result. It estimates the configuration at $38.96 per GPU-hour using DeepSeek off-peak pricing. A specialized small-batch decode path reached 826 tokens per second for one user.

Against DeepInfer, DeepSeek's offline engine, vLLM says its GB200 decode throughput was within 6% across batch sizes from 8 to 256 under DeepSeek's 131K-context configuration. Its prefill curve was compared with DeepInfer's published chart, but the hardware and setup differ, so the post does not establish an engine-to-engine prefill speed advantage.

The source reports vendor-run benchmarks and implementation details including DEP2 prefill, EPLB balancing, CPU-overhead reductions, and kernels released by DeepSeek. It does not establish equivalent performance on other models, workloads, hardware, or production deployments.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Inference](https://newruntime.com/topics/inference.md): Explore the inference topic hub.
- topic hub: [Ai Infrastructure](https://newruntime.com/topics/ai-infrastructure.md): Explore the ai-infrastructure topic hub.
- topic hub: [Compute](https://newruntime.com/topics/compute.md): Explore the compute topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)