LLM Scaling Architecture LLM Tools

Research implementations and codebases focused on scaling language models across languages, sequence lengths, and parameters—including multilingual adaptation, embedding optimization, and architectural innovations for handling massive model capacity. Does NOT include deployment infrastructure, inference optimization, or general LLM applications.

There are 42 llm scaling architecture tools tracked. 1 score above 50 (established tier). The highest-rated is aalok-sathe/surprisal at 52/100 with 51 stars. 1 of the top 10 are actively maintained.

Get all 42 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=llm-scaling-architecture&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	aalok-sathe/surprisal A unified interface for computing surprisal (log probabilities) from...	52	Established	51	Python
2	EvolvingLMMs-Lab/lmms-engine A simple, unified multimodal models training engine. Lean, flexible, and...	46	Emerging	740	Python
3	FunnySaltyFish/Better-Ruozhiba 【逐条处理完成】人为审核+修改每一条的弱智吧精选问题QA数据集	45	Emerging	253	—
4	reasoning-machines/pal PaL: Program-Aided Language Models (ICML 2023)	45	Emerging	518	Python
5	microsoft/monitors4codegen Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of...	43	Emerging	280	Python
6	YutongWang1216/DocMTAgent Code and data releases for the paper -- DelTA: An Online Document-Level...	39	Emerging	59	Roff
7	FreedomIntelligence/EchoX EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for...	39	Emerging	47	Python
8	merantix-momentum/acip 🗜️Codebase of the ACIP algorithm 🗜️	36	Emerging	16	Python
9	Mxoder/Maxs-Awesome-Datasets Max的有趣数据集 / Max's awesome datasets	33	Emerging	68	—
10	ch3njust1n/smart Self-modifying code at runtime with Large Language Models	33	Emerging	7	Python
11	apenab/pyrlm-runtime Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT...	32	Emerging	14	Python
12	ZetangForward/CSA-GEC This is the official code for ``Beyond Hard Samples: Robust and Effective...	31	Emerging	3	Python
13	zhiyuanpeng/SPTAR Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models	30	Emerging	16	Jupyter Notebook
14	farukalpay/ISO-639-2023 large language model	30	Emerging	1	—
15	zjunlp/LookAheadTuning [WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews	28	Experimental	17	Python
16	GeorgeVern/qe-fusion This repo contains the code for the paper "Don't Rank, Combine! Combining...	26	Experimental	5	Python
17	a-m-team/a-m-models a-m-team's exploration in large language modeling	25	Experimental	194	—
18	nitinvetcha/DeGAML-LLM DeGAML-LLM: Decoupling Generalization and Adaptation in Meta-Learning for...	25	Experimental	16	Python
19	Lucky-Wang-Chenlong/CodeSync [ICML25] CODESYNC: Synchronizing Large Language Models with Dynamic Code...	24	Experimental	25	Python
20	PrithwishJana/CoTran Official repository for CoTran: An LLM-based code translator for...	23	Experimental	16	Java
21	ictnlp/StreamUni StreamUni is a framework that efficiently enables unified Large...	23	Experimental	19	Python
22	LARK-AI-Lab/CodeScaler The official repo for "CodeScaler: Scaling Code LLM Training and Test-Time...	23	Experimental	32	Python
23	WSE-research/Code2Code-Translations-using-LLMs-ENASE-2026 The repository to the paper Code2Code Translations using LLMs	23	Experimental	2	Python
24	burcgokden/PLDR-LLM-Self-Organized-Criticality Code used in paper titled "PLDR-LLMs Reason at Self-Organized Criticality"	21	Experimental	—	Python
25	JingyingHu/ChineseL2Writing-Surprisals Materials and code for Hu and Cong (2025) - Modeling Chinese L2 Writing...	21	Experimental	3	R
26	hmyousuf2010/bodh A morphology-aware Bengali tokenizer for large language models.	21	Experimental	—	Rust
27	aakarsh/rl-llm-calibration-test Attempt at replication of the parts of the paper "Language models (mostly)...	21	Experimental	1	Jupyter Notebook
28	AidanCooper/constrained-decoding A guide to structured generation using constrained decoding	21	Experimental	14	Jupyter Notebook
29	tony10101105/ExpEmergence [ICLR'25] U-shaped and Inverted-U Scaling behind Emergent Abilities of Large...	19	Experimental	3	Python
30	isaacwiafe/speech_data_ghana_ug The dataset comprises of 5000 hours speech corpus in Akan, Ewe, Dagbani,...	17	Experimental	1	HTML
31	originaonxi/prm-replication Live proof of arXiv:2603.17815 — O(N) confirmed R²=0.952, 1,984 API calls	15	Experimental	1	Python
32	j-frei/CFG4FHIR Context-Free Grammar-guided Generation of FHIR Resources Using Large Language Models	14	Experimental	1	Python
33	Vidit-Ostwal/RLM-demo Recursive Language Model Demo	13	Experimental	—	TypeScript
34	lindeng0/Replication-of-LARGE-LANGUAGE-MODELS-AN-APPLIED-ECONOMETRIC-FRAMEWORK Replication of LLM econometric framework: leakage checks, prompt/model...	13	Experimental	—	Jupyter Notebook
35	sunwang-ai-linguist/bilingual-rlhf-semantic-repair-corpus Daily Mandarin-English semantic alignment corpus for RLHF training, tone...	13	Experimental	—	Python
36	aliasgar-m/Inventory-Opt-LLM A comparison between Large Language Models for Inventory Optimization	13	Experimental	—	Python
37	ymgw55/repro-superposition Unofficial implementation to reproduce the experiments from "Superposition...	13	Experimental	—	Jupyter Notebook
38	sharmavasu/SMaRT SMaRT (Small Model Reinforced Tuning) is a two-stage approach that...	12	Experimental	3	Jupyter Notebook
39	ChenDelong1999/Linguistic-Similarity Official repo of paper "Linguistic Minimal Pairs Elicit Linguistic...	12	Experimental	7	—
40	zengikun/CXK_IKUN_Dataset 蔡徐坤微调模型数据集里面包含了约100条有关于蔡徐坤，小黑子，玩梗的数据，可以用于模型微调，或者可以混合进其他数据集里，使得模型会玩坤坤的梗	11	Experimental	4	—
41	Mwaniki-Kanyi/The.Pentagon.Movement HARNESSING SEQ2SEQ vs CASUAL-LLM MODELS.	11	Experimental	—	Python
42	ArthurSpirling/LargeLanguageReplication Replication for Language Models	11	Experimental	3	—