High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogeneous engines and extreme memory efficiency for GRPO, PPO, etc.
☆434Oct 22, 2026Updated this week
Alternatives and similar repositories for RL-Kernel
Users that are interested in RL-Kernel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An LLM post-training framework with vLLM for RL Scaling☆490Oct 14, 2026Updated last week
- ☆81Oct 15, 2026Updated last week
- A vLLM-inspired inference engine for looped transformers, with loop-level scheduling and execution across composable stages☆205Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆557Updated this week
- ☆44Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- High Performance Serving Runtime For Interactive Super Intelligence System☆1,593Updated this week
- Reference implementation and examples of the CuTe Layout representation and algebra.☆380Updated this week
- ☆521Aug 26, 2026Updated last month
- Skills for writing tilelang and debugging with CUDA toolkits.☆146Updated this week
- RLVR training for LLM in CUDA/C++☆42Jul 25, 2026Updated 2 months ago
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,436Updated this week
- ☆1,046Updated this week
- DeepSelect: TopK kernels for DeepSeek Sparse Attention (DSA) and Samplers☆514Sep 30, 2026Updated 3 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,201Updated this week
- 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.
- community maintained vllm/vllm-omni style inference engine for system1 models in Rust for extreme efficient performance☆62Updated this week
- 分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等☆4,233Sep 20, 2026Updated last month
- TokenSpeed is a speed-of-light LLM inference engine.☆2,754Updated this week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆725Updated this week
- An open-source toolkit for BigMac-style pipeline-parallel training of multimodal large language models.☆37Jul 21, 2026Updated 3 months ago
- ☆57Oct 4, 2026Updated 2 weeks ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆154Jul 9, 2026Updated 3 months ago
- A linker for partial GPU kernels.☆32Oct 12, 2026Updated last week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆654Updated this week
- 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.
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,189Oct 12, 2026Updated last week
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆1,025Updated this week
- ☆304Sep 5, 2026Updated last month
- An asynchronous streaming data management module for efficient post-training.☆168Updated this week
- Ongoing research training transformer models at scale☆13Updated this week
- Efficient Mask-Aware Distributed Attention for Long-Context Training☆53Oct 16, 2026Updated last week
- Multimodal RL training framework for diffusion & omni models☆1,337Updated this week
- ☆38Aug 4, 2026Updated 2 months ago
- slime is an LLM training framework for RL Scaling.☆8,718Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆259Oct 14, 2026Updated last week
- ☆78Sep 30, 2026Updated 3 weeks ago
- Distributed Compiler and Optimized Parallel Kernels☆1,570Sep 18, 2026Updated last month
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,386May 17, 2026Updated 5 months ago
- high-performance linear attention kernel library built on TileLang☆736Oct 14, 2026Updated last week
- Mixture-of-experts (MoE) training megakernel for NVL72s☆633Oct 1, 2026Updated 3 weeks ago
- Compact and Agent-Native MoE Training System☆357Updated this week