Qwen3.5 27B DFlash Paper Github Blog This DFlash draft model is a joint retrain from Z Lab and Modal, trained with 40k sequence length and sliding window attention for improved long context performance. It is mirrored across the following Hugging Face repositories: z lab/Qwen3.5 27B DFlash modal labs/Qwen3.5 27B DFlash This repository contains a DFlash draft model for Qwen/Qwen3.5 27B . It is not a standalone language model. It is intended to be paired with the target model in a speculative decoding server. DFlash uses a lightweight block diffusion draft model to propose multiple tokens in parallel. The target model verifies those proposals, improving serving throughput while preserving the target model's output distribution. Quick Start Installation SGLang Install a recent SGLang build with DFlash support: For best performance on Blackwell GPUs, use an SGLang build that includes DFlash, FA4/TRT LLM attention, and FlashInfer support. vLLM For vLLM support, please refer to vllm project/vllm 40898. We will update the PR to make it merge ready soon. Launch Server This model should be used with an inference server that supports DFlash speculative decoding. An example SGLang deployment…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy