This is the Linux app named DFlash whose latest release can be downloaded as dflashsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named DFlash with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS
Ad
DFlash
DESCRIPTION
DFlash is an open-source framework for ultra-fast speculative decoding using a lightweight block diffusion model to draft text in parallel with a target large language model, dramatically improving inference speed without sacrificing generation quality. It acts as a “drafter” that proposes likely continuations which the main model then verifies, enabling significant throughput gains compared to traditional autoregressive decoding methods that generate token by token. This approach has been shown to deliver lossless acceleration on models like Qwen3-8B by combining block diffusion techniques with efficient batching, making it ideal for applications where latency and cost matter. The project includes support for multiple draft models, example integration code, and scripts to benchmark performance, and it is structured to work with popular model serving stacks like SGLang and the Hugging Face Transformers ecosystem.
Features
- Block diffusion based speculative decoding
- Parallel drafting for accelerated generation
- Integration examples with SGLang and Transformers
- Support for multiple draft model sizes
- Benchmarking and performance scripts
- Modular, research-friendly architecture
Programming Language
Python
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/dflash.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
