SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts
☆67Dec 1, 2025Updated 8 months ago
Alternatives and similar repositories for Spec-RL
Users that are interested in Spec-RL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆175Feb 27, 2026Updated 5 months ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆60Oct 11, 2025Updated 10 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆309Nov 7, 2025Updated 9 months ago
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆31Oct 24, 2024Updated last year
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆16Jan 16, 2026Updated 6 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Implementation of AdaCQR(COLING 2025)☆15Dec 30, 2024Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆54Oct 18, 2024Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆462Mar 20, 2026Updated 4 months ago
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model☆36Jan 8, 2025Updated last year
- [ACL 2026 (Main)] LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆86Jul 14, 2025Updated last year
- [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.☆514Mar 30, 2026Updated 4 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,077Updated this week
- (ACL2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆36May 28, 2025Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆733Apr 15, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Recent Advances on MLLM's Reasoning Ability☆26Apr 11, 2025Updated last year
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆464Jul 14, 2026Updated 3 weeks ago
- [WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer Previews☆17Dec 14, 2025Updated 7 months ago
- Official Implementation of MARS☆30Apr 21, 2026Updated 3 months ago
- RL with Experience Replay☆58Jul 27, 2025Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆1,290Jun 27, 2026Updated last month
- ☆82Jun 8, 2026Updated 2 months ago
- [EMNLP 2025🔥] UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective☆20Jan 7, 2026Updated 7 months ago
- This is the official code repository for the paper: Towards General Continuous Memory for Vision-Language Models.☆31Jul 3, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 4 months ago
- [R]einforcement [L]earning from [M]odel-rewarded [T]hinking - code for the paper "Language Models That Think, Chat Better"☆129Oct 27, 2025Updated 9 months ago
- The official implementation of the paper "A Dual-Space Framework for General Knowledge Distillation of Large Language Models".☆18Jan 4, 2026Updated 7 months ago
- ☆13Jan 14, 2025Updated last year
- Official Repo for DAC-RL: Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability☆16Feb 26, 2026Updated 5 months ago
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆24Oct 8, 2024Updated last year
- LightRFT (Light Reinforcement Fine-Tuning) is an advanced reinforcement learning fine-tuning framework designed for Large Language Models…☆19Jan 12, 2026Updated 7 months ago
- ☆27Mar 31, 2026Updated 4 months ago
- ☆22Jan 2, 2026Updated 7 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Official Code Repository for [AutoScale📈: Scale-Aware Data Mixing for Pre-Training LLMs] Published as a conference paper at **COLM 2025*…☆14Aug 8, 2025Updated last year
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆56Oct 29, 2024Updated last year
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆75Updated this week
- Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation, ICML 2024☆25Jun 26, 2024Updated 2 years ago
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆368Jan 30, 2026Updated 6 months ago
- ☆42Jul 23, 2026Updated 3 weeks ago
- A version of verl to support diverse tool use [TMLR 2026]☆1,031Jul 15, 2026Updated 3 weeks ago