LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
☆4,245Aug 27, 2026Updated this week
Alternatives and similar repositories for LightLLM
Users that are interested in LightLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- FlashInfer: Kernel Library for LLM Serving☆6,262Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆8,027Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆14,484Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,405Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,478Aug 14, 2026Updated 2 weeks ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Transformer related optimization, including BERT, GPT☆6,447Mar 27, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆974Mar 29, 2026Updated 4 months ago
- Fast and memory-efficient exact attention☆24,786Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆32,560Updated this week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,923Jan 21, 2024Updated 2 years ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,768Jun 25, 2024Updated 2 years ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,111Jun 30, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,137Sep 4, 2024Updated last year
- Large Language Model Text Generation Inference☆10,890Mar 21, 2026Updated 5 months ago
- 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.
- Development repository for the Triton language and compiler☆20,025Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,622Jul 17, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆854Mar 6, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,527Aug 12, 2026Updated 2 weeks ago
- Serving multiple LoRA finetuned LLM as one☆1,174May 8, 2024Updated 2 years ago
- Ongoing research training transformer models at scale☆17,627Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,354Aug 28, 2025Updated last year
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,898Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,292Updated 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.
- Disaggregated serving system for Large Language Models (LLMs).☆833Apr 6, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆90,225Updated this week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,505Updated this week
- fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tp…☆4,947Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,342Mar 6, 2025Updated last year
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,070Apr 11, 2025Updated last year
- how to optimize some algorithm in cuda.☆3,224Updated this week
- Efficient Triton Kernels for LLM Training☆6,590Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,316Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,512Feb 20, 2026Updated 6 months ago
- Accessible large language models via k-bit quantization for PyTorch.☆8,441Updated this week
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,268Jul 11, 2024Updated 2 years ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,349May 11, 2025Updated last year
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,325Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,677Jul 12, 2024Updated 2 years ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆687May 21, 2026Updated 3 months ago