Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs
☆109Jul 26, 2026Updated 2 months 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☆69Aug 22, 2026Updated 2 months ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 6 months ago
- [ICML2026] Reproduce Kimi K1.5/K2 RL algorithm and rollout system☆21Apr 9, 2026Updated 6 months ago
- ☆17Jun 15, 2026Updated 4 months ago
- Tinkering RL☆28Oct 16, 2026Updated last 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.
- An LLM post-training framework with vLLM for RL Scaling☆490Oct 14, 2026Updated last week
- A Multi-Policy, Multi-Agent RL Training Framework☆32Jun 16, 2026Updated 4 months ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,182Updated this week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆650Updated this week
- ☆17May 27, 2026Updated 4 months ago
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆30Apr 17, 2026Updated 6 months ago
- [ICML 2025] Adaptive Self-improvement LLM Agentic System for ML Library Development☆17Jan 6, 2026Updated 9 months ago
- Allow torch tensor memory to be released and resumed later☆281Sep 29, 2026Updated 3 weeks ago
- An asynchronous streaming data management module for efficient post-training.☆166Oct 15, 2026Updated last 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.
- Compact and Agent-Native MoE Training System☆357Updated this week
- Agentic RL on Any Harness at Scale☆862Oct 7, 2026Updated 2 weeks ago
- Bridge Megatron-Core to Hugging Face/Reinforcement Learning☆233Oct 10, 2026Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆257Dec 16, 2024Updated last year
- SkyRL: A Modular Full-stack RL Library for LLMs☆2,443Updated this week
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 10 months ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- Accelerating MoE with IO and Tile-aware Optimizations☆781Aug 29, 2026Updated last month
- ☆17Mar 24, 2026Updated 6 months ago
- 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.
- Can AI Agents Build Bespoke Systems?☆118Updated this week
- ☆13Oct 13, 2025Updated last year
- ☆44Jul 23, 2026Updated 3 months ago
- Build and train systems of agents.☆32Updated this week
- DeepStack: Facilitating Co-Design Exploration of 3D DRAM-Stacked Accelerators for Distributed LLM Inference. Includes the MICRO 2026 AE a…☆65Oct 5, 2026Updated 2 weeks ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆295Sep 25, 2026Updated 3 weeks ago
- APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation. A system-level optimization for scalable LLM tra…☆64Oct 11, 2025Updated last year
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆308Nov 7, 2025Updated 11 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆153Nov 10, 2025Updated 11 months ago
- 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.
- 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
- [ASPLOS' 26] TetriServe: Efficiently Serving Mixed DiT Workloads☆20Mar 12, 2026Updated 7 months ago
- A simple, fast and robust program-aware agentic inference system.☆467Jul 5, 2026Updated 3 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆437Aug 5, 2026Updated 2 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆296Updated this week
- ☆66May 7, 2026Updated 5 months ago
- SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.☆19Oct 9, 2026Updated 2 weeks ago