ShopeeLLM / Spec-RLLinks
SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts
☆57Updated last month
Alternatives and similar repositories for Spec-RL
Users that are interested in Spec-RL are comparing it to the libraries listed below
Sorting:
- ☆126Updated 7 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆54Updated last year
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆39Updated 10 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- ☆41Updated 9 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆110Updated 2 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆61Updated 10 months ago
- Dynamic Context Selection for Efficient Long-Context LLMs☆50Updated 7 months ago
- ☆49Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆281Updated 2 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆45Updated 3 months ago
- This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"☆55Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆216Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 9 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆144Updated 2 weeks ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆121Updated last month
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆213Updated 4 months ago
- ☆29Updated 3 months ago
- ☆299Updated 6 months ago
- ☆49Updated 7 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆123Updated last month
- ☆90Updated 6 months ago
- ☆143Updated 3 months ago
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆119Updated last year
- Code for the preprint "Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?"☆47Updated 5 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆72Updated 5 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆61Updated 3 months ago
- ☆109Updated 3 months ago
- ☆31Updated 2 months ago
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆58Updated 2 months ago