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.
☆408Oct 2, 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++.☆553Sep 20, 2026Updated last week
- Skills for writing tilelang and debugging with CUDA toolkits.☆144Sep 15, 2026Updated 2 weeks ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,307Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆480Updated this week
- ☆484Aug 26, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆28Mar 31, 2026Updated 6 months ago
- RLVR training for LLM in CUDA/C++☆42Jul 25, 2026Updated 2 months ago
- ☆881Sep 22, 2026Updated last week
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆148Jul 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☆4,096Sep 20, 2026Updated last week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆715Updated this week
- Multimodal RL training framework for diffusion & omni models☆1,147Updated 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 3 months ago
- Compact and Agent-Native MoE Training System☆355Sep 23, 2026Updated last week
- 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.
- A from-scratch Prefill/Decode disaggregation inference engine for LLMs☆160May 10, 2026Updated 4 months ago
- ☆55Apr 16, 2026Updated 5 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…☆210Updated this week
- An asynchronous streaming data management module for efficient post-training.☆158Sep 24, 2026Updated last week
- ☆97Sep 15, 2025Updated last year
- TokenSpeed is a speed-of-light LLM inference engine.☆2,189Updated this week
- A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).☆1,164Updated this week
- A demonstrative example of running SGLang Diffusion with DP router☆25Mar 15, 2026Updated 6 months ago
- ☆293Sep 5, 2026Updated 3 weeks ago
- 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.
- 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☆7,026Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,207May 17, 2026Updated 4 months ago
- A Large-Scale Computation Graph Database for Tensor Compiler Research☆98May 22, 2026Updated 4 months ago
- UniRL is a Framework for Unified Multimodal Model Reinforcement Learning☆1,001Updated this week
- ☆27Oct 1, 2025Updated last year
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆635Updated this week
- [Archived] For the latest updates and community contribution, please visit: https://github.com/Ascend/TransferQueue or https://gitcode.co…☆15Aug 14, 2026Updated last month
- High Performance LLM Inference Operator Library☆1,171Sep 7, 2026Updated 3 weeks ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆177Updated this week
- ☆44Jul 23, 2026Updated 2 months ago
- ☆389Jan 28, 2026Updated 8 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,703Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,555Sep 18, 2026Updated 2 weeks ago
- A Triton JIT runtime and ffi provider in C++☆41Sep 24, 2026Updated last week
- slime is an LLM post-training framework for RL Scaling.☆8,586Updated this week