OpenGVLab/SDLM
Sequential Diffusion Language Model (SDLM) enhances pre-trained autoregressive language models by adaptively determining generation length and maintaining KV-cache compatibility, achieving high efficiency and throughput.
This project offers an enhanced way to generate text using large language models (LLMs), allowing you to get answers faster without sacrificing quality. It takes your prompt (like a question or a request for code) and quickly produces a high-quality, relevant text response. Data scientists, machine learning engineers, and researchers working with LLMs will find this useful for speeding up text generation tasks.
Use this if you need to generate text with pre-trained autoregressive language models and want significantly faster decoding speeds while maintaining high accuracy.
Not ideal if you are primarily focused on training new base language models from scratch or if you require extreme fine-grained control over token-by-token generation for highly specialized research.
Stars
92
Forks
3
Language
Python
License
MIT
Category
Last pushed
Dec 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenGVLab/SDLM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ljleb/sd-mecha
Executable State Dict Recipes
SJTU-DENG-Lab/Discrete-Diffusion-Forcing
Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference
declare-lab/tango
A family of diffusion models for text-to-audio generation.
Li-Jinsong/DAEDAL
[ICLR 2026] Official repository of "Beyond Fixed: Training-Free Variable-Length Denoising for...
SalesforceAIResearch/CoDA
Salesforce AI Research's open diffusion language model