Qwen3.5 397B A17B DFlash Paper Github Blog This is a joint release collaboration between Z Lab, Modal, and SGLang. The draft model is mirrored across the following Hugging Face repositories: z lab/Qwen3.5 397B A17B DFlash modal labs/Qwen3.5 397B A17B DFlash lmsys/Qwen3.5 397B A17B DFlash This repository contains a DFlash draft model for Qwen/Qwen3.5 397B A17B . 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 DFlash serving requires a recent SGLang build. We recommend installing SGLang from a commit at or after ec36dde58083aca8f26c3740332498a11a06debf , which includes DFlash v2 overlap scheduling, DFlash sliding window draft attention, and the required FlashInfer integration. For production serving, use a CUDA image with Blackwell support, such as lmsysorg/sglang:v0.5.13 cu130 , and install the pinned SGLang commit inside the image. Launch Server This model should b…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy