Alternatives and similar repositories for speculative_thinking

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

• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆31Updated 6 months ago
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]
  ☆49Updated last month
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆51Updated 10 months ago
• OpenSparseLLMs / Linear-MoE
  ☆117Updated 2 months ago
• mutonix / pyramidinfer
  ☆45Updated 9 months ago
• abdelfattah-lab / SplitReason
  ☆18Updated 2 months ago
• Linking-ai / SCOPE
  (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation
  ☆32Updated 3 months ago
• StarDewXXX / O1-Pruner
  Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
  ☆87Updated 6 months ago
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆102Updated last month
• GeniusHTX / TALE
  ☆130Updated 2 weeks ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆53Updated 6 months ago
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆23Updated 10 months ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆110Updated 4 months ago
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆113Updated 8 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆184Updated this week
• bethgelab / sober-reasoning
  A Sober Look at Language Model Reasoning
  ☆81Updated 2 months ago
• TemporaryLoRA / Block-Attention
  ☆33Updated 5 months ago
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆63Updated last month
• sail-sg / SimLayerKV
  The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.
  ☆48Updated 10 months ago
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆190Updated this week
• zhenyuhe00 / SWE-Swiss
  SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution
  ☆78Updated this week
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆41Updated last month
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆92Updated 2 months ago
• thu-wyz / inference_scaling
  ☆74Updated 9 months ago
• UCSB-NLP-Chang / ThinkPrune
  ☆41Updated 4 months ago
• liushulinle / UloRL
  An Ultra-Long Output Reinforcement Learning Approach
  ☆20Updated last month
• MingyuJ666 / Rope_with_LLM
  [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…
  ☆80Updated 2 months ago
• WANGXinyiLinda / planning_tokens
  Official code for Guiding Language Model Math Reasoning with Planning Tokens
  ☆15Updated last year
• hemingkx / TokenSkip
  [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs
  ☆177Updated 2 months ago
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆77Updated 5 months ago