A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
☆4,628May 17, 2026Updated 2 months ago
Alternatives and similar repositories for mini-sglang
Users that are interested in mini-sglang are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Nano vLLM☆14,627Apr 26, 2026Updated 2 months ago
- My learning notes for ML SYS.☆6,768Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,018Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,706Updated this week
- slime is an LLM post-training framework for RL Scaling.☆7,621Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,784Updated this week
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆11,621Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,986Updated this week
- Materials for learning SGLang☆860Jan 5, 2026Updated 6 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,871Updated this week
- SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models☆692Updated this week
- 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☆3,115Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,256Aug 26, 2025Updated 10 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆22,649Updated this week
- 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.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆10,860Updated this week
- TokenSpeed is a speed-of-light LLM inference engine.☆1,657Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆732Jul 4, 2026Updated 3 weeks ago
- Distributed Compiler based on Triton for Parallel Systems☆1,498Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,589Jul 14, 2026Updated last week
- Minimalistic large language model 3D-parallelism training☆2,764May 26, 2026Updated last month
- A Datacenter Scale Distributed Inference Serving Framework☆7,574Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,554Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,007Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆87,069Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,409Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,596Updated this week
- A framework for efficient model inference with omni-modality models☆5,680Updated this week
- High Performance LLM Inference Operator Library☆1,063Updated this week
- A Quirky Assortment of CuTe Kernels☆1,070Updated this week
- A kernel library written in tilelang☆1,661Apr 23, 2026Updated 3 months ago
- A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.☆4,405Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,123Updated 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.
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆937Updated this week
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,121Updated this week
- Tile primitives for speedy kernels☆3,563Jul 13, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,345Aug 28, 2025Updated 10 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,390Updated this week
- Puzzles for learning Triton☆2,537Apr 1, 2026Updated 3 months ago
- NVIDIA Inference Xfer Library (NIXL)☆1,149Updated this week