Speculative Decoding Algorithms Transformer Models

There are 18 speculative decoding algorithms models tracked. 1 score above 70 (verified tier). The highest-rated is sgl-project/SpecForge at 79/100 with 729 stars. 1 of the top 10 are actively maintained.

Get all 18 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=speculative-decoding-algorithms&limit=20"

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

#	Model	Score	Tier	Stars	Language
1	sgl-project/SpecForge Train speculative decoding models effortlessly and port them smoothly to...	79	Verified	729	Python
2	structuredllm/syncode Efficient and general syntactical decoding for Large Language Models	61	Established	328	Python
3	SafeAILab/EAGLE Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and...	57	Established	2,213	Python
4	romsto/Speculative-Decoding Implementation of the paper Fast Inference from Transformers via Speculative...	45	Emerging	101	Python
5	hao-ai-lab/JacobiForcing Jacobi Forcing: Fast and Accurate Diffusion-style Decoding	43	Emerging	143	Python
6	kssteven418/BigLittleDecoder [NeurIPS'23] Speculative Decoding with Big Little Decoder	39	Emerging	96	Python
7	torchspec-project/TorchSpec A PyTorch native library for training speculative decoding models	37	Emerging	32	Python
8	BaohaoLiao/RSD [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and...	35	Emerging	56	Python
9	Infini-AI-Lab/Sequoia scalable and robust tree-based speculative decoding algorithm	34	Emerging	372	Python
10	mscheong01/speculative_decoding.c minimal C implementation of speculative decoding based on llama2.c	30	Emerging	28	C
11	Infini-AI-Lab/TriForce [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with...	30	Emerging	277	Python
12	ZhouYuxuanYX/Benchmarking-and-Guiding-Adaptive-Sampling-Decoding-for-LLMs This is the official implementation of our ACL 2025 Main paper "Balancing...	25	Experimental	17	Python
13	hsj576/GTO Official Implementation of "Bridging Draft Policy Misalignment: Group Tree...	24	Experimental	3	Python
14	OdedMous/DP-Decoding-in-LLM Experiment a differentially private decoding strategy for LLMs.	22	Experimental	2	HTML
15	CyberCoder-IITM/HaloSpec Adaptive speculative decoding benchmark with runtime perturbation and...	21	Experimental	—	Rust
16	levvius/adaptive-speculative-decoding Adaptive speculative decoding for LLM inference latency optimization	21	Experimental	—	Python
17	Hassan-Sarwat/efficient-speculative-decoding Improving both reasoning speed of LLM using Chain of Draft fine tuning and...	13	Experimental	—	Jupyter Notebook
18	pinqian77/Dynasurge Dynasurge: Dynamic Tree Speculation for Prompt-Specific Decoding	10	Experimental	2	Python

Comparisons in this category

SpecForge and TorchSpec (79 vs 37)