---
title: "Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding"
url: https://daily.dev/posts/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding-yeogdqdwe
source_url: https://developer.nvidia.com/blog/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding
type: article
source: "NVIDIA Developer"
published: 2026-06-23T15:03:44.726Z
updated: 2026-06-23T15:06:02.976Z
tags: ["ai-inference", "vllm"]
reading_time: 7
upvotes: 0
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding

**[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 7 min read · 0 upvotes · 0 comments

## Summary

DFlash is an open source block-diffusion speculative decoding method that replaces sequential autoregressive drafting with parallel block-level token prediction. On NVIDIA Blackwell hardware, it delivers up to 15x throughput improvement over autoregressive decoding for gpt-oss-120b at high interactivity targets, and outperforms EAGLE-3 speculative decoding by 1.5x. The technique uses three key mechanisms: block-diffusion drafting, target hidden-state conditioning, and KV injection. Twenty model checkpoints covering Qwen, Llama, Gemma, Kimi K2.6, and gpt-oss families are available on Hugging Face, with integration support for TensorRT-LLM, vLLM (via the Speculators library), and SGLang requiring minimal config changes and no application refactoring.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://developer.nvidia.com/blog/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding>

## Similar posts on daily.dev

- [Speculative Decoding on CPUs: Nearly 4x Faster Token Generation with DFlash](https://daily.dev/posts/speculative-decoding-on-cpus-nearly-4x-faster-token-generation-with-dflash-suiryhqim) · Towards Data Science · 0 upvotes · 0 comments
- [Supercharging LLM inference on Google TPUs: Achieving 3X speedups with diffusion-style speculative decoding](https://daily.dev/posts/supercharging-llm-inference-on-google-tpus-achieving-3x-speedups-with-diffusion-style-speculative-d-jiflbzrv8) · Google Developers · 0 upvotes · 0 comments

---

Tags: [#ai-inference](https://daily.dev/tags/ai-inference), [#vllm](https://daily.dev/tags/vllm)

[View this post on daily.dev](https://daily.dev/posts/boost-inference-performance-up-to-15x-on-nvidia-blackwell-using-dflash-speculative-decoding-yeogdqdwe)