APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM training.
☆63Oct 11, 2025Updated 10 months ago
Alternatives and similar repositories for APRIL
Users that are interested in APRIL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆44Jul 23, 2026Updated last month
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆15Aug 14, 2026Updated 2 weeks ago
- A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.☆20Aug 4, 2026Updated 3 weeks ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 5 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆152Nov 10, 2025Updated 9 months ago
- 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.
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆34Apr 27, 2026Updated 4 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 9 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,288Updated this week
- SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts☆67Dec 1, 2025Updated 8 months ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆116Dec 17, 2025Updated 8 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 9 months ago
- ☆99Sep 15, 2025Updated 11 months ago
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆173Aug 20, 2026Updated last week
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆405Mar 30, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,003Aug 12, 2026Updated 2 weeks ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆176Feb 27, 2026Updated 6 months ago
- On demand communication☆33Apr 16, 2026Updated 4 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,210Updated this week
- ☆19Oct 2, 2023Updated 2 years ago
- Allow torch tensor memory to be released and resumed later☆272Aug 21, 2026Updated last week
- An implementation of online data mixing for the Pile dataset, based on the GPT-NeoX library.☆14Jan 9, 2024Updated 2 years ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆145Dec 17, 2025Updated 8 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆230Jun 15, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- verl Zero-Mismatch Dense/MoE HuggingFace Rollout☆68Aug 5, 2026Updated 3 weeks ago
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 3 months ago
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆580Updated this week
- MrlX: A Multi-Agent Reinforcement Learning Framework☆221Jan 19, 2026Updated 7 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 4 months ago
- Ongoing research training transformer models at scale☆19Updated this week
- An agent for CUDA compute-communication kernel co-design☆36May 7, 2026Updated 3 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,313Updated this week
- Compact and Agent-Native MoE Training System☆345Aug 22, 2026Updated last week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- An LLM post-training framework with vLLM for RL Scaling☆443Updated this week
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆928Updated this week
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated 2 months ago
- ☆98Updated this week
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Jun 5, 2026Updated 2 months ago
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆18Jan 15, 2025Updated last year
- This is the repository for our EMNLP 2022 paper "The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains".☆10Jun 2, 2023Updated 3 years ago