Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs
☆102Jul 26, 2026Updated 3 weeks ago
Alternatives and similar repositories for astraflow
Users that are interested in astraflow are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆68Updated this week
- [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
- [ICML2026] Reproduce Kimi K1.5/K2 RL algorithm and rollout system☆21Apr 9, 2026Updated 4 months ago
- Tinkering RL☆28Updated this week
- ☆17Jun 15, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,216Updated this week
- ☆16May 27, 2026Updated 2 months ago
- An LLM post-training framework with vLLM for RL Scaling☆428Updated this week
- A Multi-Policy, Multi-Agent RL Training Framework☆32Jun 16, 2026Updated 2 months ago
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆578Updated this week
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆30Apr 17, 2026Updated 4 months ago
- [ICML 2025] Adaptive Self-improvement LLM Agentic System for ML Library Development☆17Jan 6, 2026Updated 7 months ago
- Can AI Agents Build Bespoke Systems?☆92Updated this week
- Compact and Agent-Native MoE Training System☆338Updated 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.
- Agentic RL on Any Harness at Scale☆802Aug 13, 2026Updated last week
- An asynchronous streaming data management module for efficient post-training.☆135Updated this week
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆22Nov 28, 2025Updated 8 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- ☆16Mar 24, 2026Updated 5 months ago
- ☆13Oct 13, 2025Updated 10 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆747Aug 17, 2026Updated last week
- Building the Virtuous Cycle for AI-driven LLM Systems☆268May 1, 2026Updated 3 months ago
- Allow torch tensor memory to be released and resumed later☆271Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,188Updated this week
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆18Mar 12, 2026Updated 5 months ago
- A simple, fast and robust program-aware agentic inference system.☆421Jul 5, 2026Updated last month
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆433Aug 5, 2026Updated 2 weeks ago
- An agentic-first RL framework for research (9k lines).☆945Updated this week
- NexRL is an ultra-loosely-coupled LLM post-training framework.☆118Jul 30, 2026Updated 3 weeks ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- The open-source agent-serving project☆482Jul 16, 2026Updated last month
- ☆46Oct 15, 2025Updated 10 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.
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆36May 22, 2026Updated 3 months ago
- Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.☆55Jul 8, 2026Updated last month
- ☆66May 7, 2026Updated 3 months ago
- ☆35Oct 8, 2025Updated 10 months ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆230Jun 15, 2026Updated 2 months ago
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 9 months ago