Alternatives and similar repositories for nanovppo

Users that are interested in nanovppo are comparing it to the libraries listed below

• rlite-project / RLite
  A lightweight reinforcement learning framework that integrates seamlessly into your codebase, empowering developers to focus on algorithm…
  ☆48Updated this week
• yyht / openrlhf_async_pipline
  ☆72Updated last week
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆155Updated this week
• MiniMax-AI / SynLogic
  The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  ☆163Updated last month
• LCLM-Horizon / A-Comprehensive-Survey-For-Long-Context-Language-Modeling
  A Comprehensive Survey on Long Context Language Modeling
  ☆176Updated last month
• RUC-GSAI / YuLan-Mini
  A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.
  ☆208Updated last month
• agentica-project / verl-pipeline
  Async pipelined version of Verl
  ☆117Updated 4 months ago
• princeton-nlp / ProLong
  Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
  ☆221Updated 5 months ago
• princeton-pli / MeCo
  Code for ICML 25 paper "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"
  ☆41Updated last month
• ScalingIntelligence / large_language_monkeys
  ☆101Updated 11 months ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆188Updated 2 months ago
• SynthLabsAI / big-math
  A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
  ☆60Updated 6 months ago
• step-law / steplaw
  ☆199Updated 4 months ago
• TIGER-AI-Lab / General-Reasoner
  General Reasoner: Advancing LLM Reasoning Across All Domains
  ☆163Updated 2 months ago
• facebookresearch / PhysicsLM4
  Physics of Language Models, Part 4
  ☆232Updated 3 weeks ago
• LLM360 / MegaMath
  [COLM 2025] An Open Math Pre-trainng Dataset with 370B Tokens.
  ☆98Updated 4 months ago
• QwenLM / WorldPM
  ☆90Updated 3 months ago
• microsoft / LongRoPE
  LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
  ☆241Updated last year
• bigai-nlco / TokenSwift
  [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  ☆113Updated 3 months ago
• shizhediao / Post-Training-Data-Flywheel
  We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.
  ☆58Updated 10 months ago
• shaochenze / PatchTrain
  Code for paper "Patch-Level Training for Large Language Models"
  ☆86Updated 9 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆432Updated 3 months ago
• princeton-nlp / CEPE
  [ACL 2024] Long-Context Language Modeling with Parallel Encodings
  ☆157Updated last year
• zwhe99 / DeepMath
  A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
  ☆244Updated 2 months ago
• Leooyii / LCEG
  Long Context Extension and Generalization in LLMs
  ☆58Updated 11 months ago
• Infini-AI-Lab / gsm_infinite
  ☆51Updated 2 months ago
• mathllm / MathCoder2
  ☆69Updated 10 months ago
• TIGER-AI-Lab / CritiqueFineTuning
  Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
  ☆170Updated last month
• eddycmu / demystify-long-cot
  ☆312Updated 2 months ago
• eric-haibin-lin / verl-community
  ☆26Updated last week