Alternatives and similar repositories for NexGAP

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

• openpsi-project / ReaLHF
  Super-Efficient RLHF Training of LLMs with Parameter Reallocation
  ☆330Updated 8 months ago
• nex-agi / Nex-N1
  ☆97Updated last month
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆61Updated 3 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆281Updated 2 months ago
• ISEEKYAN / mbridge
  Bridge Megatron-Core to Hugging Face/Reinforcement Learning
  ☆181Updated this week
• ByteDance-Seed / ByteCheckpoint
  ByteCheckpoint: An Unified Checkpointing Library for LFMs
  ☆258Updated last month
• HArmonizedSS / HASS
  Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)
  ☆52Updated 9 months ago
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆348Updated 3 months ago
• nex-agi / NexRL
  NexRL is an ultra-loosely-coupled LLM post-training framework.
  ☆63Updated last month
• hemingkx / Spec-Bench
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆350Updated 8 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆144Updated 2 weeks ago
• LiuXiaoxuanPKU / OSD
  ☆64Updated last year
• tongyx361 / symeval
  Evaluation utilities based on SymPy.
  ☆21Updated last year
• mit-han-lab / fastrl
  [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
  ☆121Updated last month
• GeeeekExplorer / 3d-parallel-demo
  使用torch.distributed实现DP/TP/PP
  ☆12Updated 2 years ago
• step-law / steplaw
  ☆208Updated 2 months ago
• mutonix / pyramidinfer
  ☆49Updated last year
• ISEEKYAN / verl_megatron_practice
  (best/better) practices of megatron on veRL and tuning guide
  ☆114Updated 3 months ago
• AIoT-MLSys-Lab / D2O
  [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
  ☆25Updated 6 months ago
• Blueyee / Efficient-CoT-LRMs
  Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!
  ☆71Updated 9 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆214Updated 10 months ago
• FMInference / H2O
  [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
  ☆498Updated last year
• WooooDyy / BAPO
  Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…
  ☆89Updated 2 months ago
• maomaocun / dLLM-cache
  Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…
  ☆191Updated last month
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆49Updated 5 months ago
• Multiverse4FM / Multiverse
  ☆90Updated 6 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆362Updated 6 months ago
• stepfun-ai / Step3
  ☆443Updated 5 months ago
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆615Updated this week
• wumingqi / LLM-Math-Evaluation
  Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.
  ☆21Updated 5 months ago