A simple, fast and robust program-aware agentic inference system.
☆373Jul 5, 2026Updated 2 weeks ago
Alternatives and similar repositories for ThunderAgent
Users that are interested in ThunderAgent are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Preview Code for Continuum Paper☆89Jul 13, 2026Updated last week
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆67Jun 24, 2026Updated 3 weeks ago
- mKernel: fast multi-node, multi-GPU fused kernels☆251Jun 21, 2026Updated 3 weeks ago
- Compact and Agent-Native MoE Training System☆288Updated this week
- Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"☆29Apr 17, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆16May 27, 2026Updated last month
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆174Feb 27, 2026Updated 4 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆731Jul 4, 2026Updated 2 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,754Updated this week
- The open-source agent-serving project☆481Updated this week
- ☆35Jan 27, 2026Updated 5 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆21Nov 28, 2025Updated 7 months ago
- ☆754Jun 2, 2026Updated last month
- ☆250Nov 19, 2025Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Coco is a proactive co-assistant that connects user workspace with a broader ecosystem of AI agents.☆17Updated this week
- [MLSys 26] 🥇 Solution for Gated Delta Net Track of MLSys 26 Flash infer competition☆35May 22, 2026Updated last month
- Building the Virtuous Cycle for AI-driven LLM Systems☆259May 1, 2026Updated 2 months ago
- ☆15Jun 10, 2022Updated 4 years ago
- [NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.☆19Mar 30, 2026Updated 3 months ago
- ☆71Mar 24, 2026Updated 3 months ago
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆28Apr 27, 2026Updated 2 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆306Nov 7, 2025Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,983Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- A comprehensive benchmarking framework for evaluating and optimizing CPU-centric agentic AI systems across multiple workloads, reproducin…☆47Feb 12, 2026Updated 5 months ago
- TokenSpeed is a speed-of-light LLM inference engine.☆1,629Updated this week
- ☆309Jun 9, 2026Updated last month
- Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs☆95Updated this week
- [ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆104May 8, 2026Updated 2 months ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,852May 20, 2026Updated 2 months ago
- A framework for generating realistic LLM serving workloads☆161May 11, 2026Updated 2 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated last year
- [CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.☆3,728Jun 10, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 3 months ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,465Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆280Jul 6, 2025Updated last year
- Automated High-Performance GPU Kernel Generation☆120Jun 1, 2026Updated last month
- An LLM post-training framework with vLLM for RL Scaling☆373Updated this week
- An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale☆506Updated this week
- Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference☆4,991Updated this week