A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
☆5,147May 17, 2026Updated 4 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☆15,600Apr 26, 2026Updated 4 months ago
- My learning notes for ML SYS.☆7,396Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,495Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,377Updated this week
- slime is an LLM post-training framework for RL Scaling.☆8,524Updated 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.
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,979Updated this week
- Open-source book with Modern CUDA Learn Notes for Beginners, includes FP16/BF16, FP8, HGEMM, FlashAttention, CuTe, etc.☆11,996Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,647Updated this week
- Materials for learning SGLang☆893Jan 5, 2026Updated 8 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,464Updated this week
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,263Updated 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☆4,033Updated this week
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,311Aug 26, 2025Updated last year
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,583Updated 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.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,895Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆769Aug 29, 2026Updated 3 weeks ago
- TokenSpeed is a speed-of-light LLM inference engine.☆2,164Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,794Aug 13, 2026Updated last month
- Distributed Compiler and Optimized Parallel Kernels☆1,552Updated this week
- Minimalistic large language model 3D-parallelism training☆2,827Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,151Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,863Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,189Updated 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☆92,527Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,786Updated this week
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,791Updated this week
- A framework for efficient model inference with omni-modality models☆7,024Updated this week
- High Performance LLM Inference Operator Library☆1,167Sep 7, 2026Updated 2 weeks ago
- A Quirky Assortment of CuTe Kernels☆1,152Updated this week
- A kernel library written in tilelang☆1,775Apr 23, 2026Updated 5 months ago
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,706Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,475Updated 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.
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,150Updated this week
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆1,043Aug 29, 2026Updated 3 weeks ago
- Tile primitives for speedy kernels☆3,725Sep 12, 2026Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆1,266Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,364Aug 28, 2025Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,511Updated this week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,005Sep 15, 2026Updated last week