Diffusion Language Models LLM Tools

Tools and techniques for training, optimizing, and decoding diffusion-based language models. Includes memory enhancement, length extrapolation, constrained decoding, and inference acceleration for diffusion LLMs. Does NOT include standard autoregressive LLMs, general diffusion models for image generation, or non-diffusion-based language model architectures.

There are 15 diffusion language models tools tracked. The highest-rated is zhenye234/xcodec at 39/100 with 294 stars.

Get all 15 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=diffusion-language-models&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	zhenye234/xcodec AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec...	39	Emerging	294	Python
2	zhuhanqing/APOLLO APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper...	35	Emerging	271	Python
3	Y-Research-SBU/CSRv2 Official Repository for CSRv2 - ICLR 2026	24	Experimental	10	Python
4	HITESHLPATEL/Mamba-Papers Awesome Mamba Papers: A Curated Collection of Research Papers , Tutorials & Blogs	23	Experimental	26	—
5	MouxiaoHuang/PPE [ICLR 2026] Official code of PPE: Positional Preservation Embedding for...	22	Experimental	3	Python
6	psychofict/llm-effective-context-length Investigating Why the Effective Context Length of LLMs Falls Short (Based on...	22	Experimental	—	Python
7	rishikksh20/mamba3-pytorch Readable implementation of Mamba 3 SSM model	18	Experimental	7	Python
8	sayhitosandy/Mamba_SSM Mamba: Linear-Time Sequence Modeling with Selective State Spaces	16	Experimental	3	—
9	hrlics/CoPE CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs	16	Experimental	10	Python
10	yophis/decom-renorm-merge Decom-Renorm-Merge: Merging deep learning models through shared representation space.	16	Experimental	1	Python
11	chen-hao-chao/mdm-prime-v2 MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Compute-optimal...	16	Experimental	2	Python
12	aflah02/Partial_RoPE_Analysis Code accompanying the paper “Fractional Rotation, Full Potential?...	15	Experimental	1	Shell
13	Anri-Lombard/Mamba-SAFE Generating Molecules with the Mamba architecture	13	Experimental	5	Jupyter Notebook
14	Ghost---Shadow/diff-bleu A fully vectorized PyTorch implementation of BLEU scores optimized for...	11	Experimental	—	—
15	Ghost---Shadow/diff-rouge A fully vectorized PyTorch implementation of ROUGE scores optimized for...	11	Experimental	—	Python