Alternatives and similar repositories for IRT-Router

Users that are interested in IRT-Router are comparing it to the libraries listed below

• LiuXiaoxuanPKU / OSD
  ☆60Updated 11 months ago
• pettingllms-ai / PettingLLMs
  A RL Framework for multi LLM agent system
  ☆63Updated last month
• ruipeterpan / specreason
  PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
  ☆58Updated last month
• uservan / speculative_thinking
  ☆29Updated last month
• hdong920 / GRIFFIN
  ☆39Updated last year
• pan-x-c / EE-LLM
  EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
  ☆70Updated last year
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆47Updated 4 months ago
• henryzhongsc / longctx_bench
  Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…
  ☆86Updated 8 months ago
• Jingyu6 / speculative_prefill
  ☆46Updated 6 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆47Updated last year
• ZO-Bench / ZO-LLM
  [ICML‘24] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".
  ☆117Updated 4 months ago
• hao-ai-lab / Dynasor
  [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
  ☆206Updated 5 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆36Updated 9 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆130Updated 3 weeks ago
• Infini-AI-Lab / APE
  ☆34Updated 9 months ago
• Persdre / NeurIPS-2024-LLM-Papers
  Accepted LLM Papers in NeurIPS 2024
  ☆37Updated last year
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆64Updated last year
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆146Updated 9 months ago
• BaohaoLiao / RSD
  [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
  ☆51Updated 6 months ago
• falcon-xu / early-exit-papers
  A curated list of early exiting (LLM, CV, NLP, etc)
  ☆68Updated last year
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆114Updated 3 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆93Updated 2 years ago
• RLsys-Foundation / APRIL
  APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…
  ☆43Updated last month
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆209Updated 9 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆275Updated 2 weeks ago
• RLsys-Foundation / TritonForge
  🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…
  ☆99Updated last week
• Jikai0Wang / Speculative_CoT
  ☆19Updated 6 months ago
• Guangxuan-Xiao / GSM8K-eval
  ☆54Updated 2 years ago
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆41Updated last year
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆63Updated last year