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.
☆296Sep 12, 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:
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆545Updated this week
- Skills for writing tilelang and debugging with CUDA toolkits.☆137May 20, 2026Updated 3 months ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,165Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆458Updated this week
- ☆446Aug 26, 2026Updated 2 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆28Mar 31, 2026Updated 5 months ago
- RLVR training for LLM in CUDA/C++☆42Jul 25, 2026Updated last month
- ☆814Updated this week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆146Jul 9, 2026Updated 2 months ago
- 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☆3,896Aug 7, 2026Updated last month
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆686Updated this week
- Multimodal RL training framework for diffusion & omni models☆1,012Updated this week
- 面向数据领域专业人士的skills技能库，个人平常使用☆16Jun 17, 2026Updated 2 months ago
- A from-scratch Prefill/Decode disaggregation inference engine for LLMs☆166May 10, 2026Updated 4 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.
- Compact and Agent-Native MoE Training System☆349Updated this week
- ☆54Apr 16, 2026Updated 4 months ago
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆203Updated this week
- An asynchronous streaming data management module for efficient post-training.☆149Updated this week
- ☆99Sep 15, 2025Updated 11 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,116Updated this week
- An agentic-first RL framework for research (9k lines).☆1,031Updated this week
- A demonstrative example of running SGLang Diffusion with DP router☆19Mar 15, 2026Updated 5 months ago
- ☆278Sep 5, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆64Oct 11, 2025Updated 11 months ago
- A framework for efficient model inference with omni-modality models☆6,774Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,032May 17, 2026Updated 3 months ago
- A Large-Scale Computation Graph Database for Tensor Compiler Research☆96May 22, 2026Updated 3 months ago
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆954Updated this week
- ☆27Oct 1, 2025Updated 11 months ago
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆603Updated this week
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆15Aug 14, 2026Updated 3 weeks ago
- ☆34Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- High Performance LLM Inference Operator Library☆1,157Updated this week
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆175Aug 20, 2026Updated 3 weeks ago
- ☆45Jul 23, 2026Updated last month
- ☆385Jan 28, 2026Updated 7 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,562Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,544Aug 12, 2026Updated last month
- A Triton JIT runtime and ffi provider in C++☆40Updated this week