LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
☆4,364Nov 17, 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☆6,949Updated this week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆8,149Updated 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…☆15,084Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆7,061Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,565Oct 20, 2026Updated 3 weeks ago
- 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.
- Transformer related optimization, including BERT, GPT☆6,460Mar 27, 2024Updated 2 years ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,981Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆978Mar 29, 2026Updated 7 months ago
- Fast and memory-efficient exact attention☆25,312Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,118Jun 30, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,178Sep 4, 2024Updated 2 years ago
- 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☆2,776Jun 25, 2024Updated 2 years ago
- Large Language Model Text Generation Inference☆10,876Mar 21, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Development repository for the Triton language and compiler☆20,590Updated this week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,667Jul 17, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,580Sep 18, 2026Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆869Mar 6, 2025Updated last year
- Ongoing research training transformer models at scale☆18,426Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,379Aug 28, 2025Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆97,102Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,176May 8, 2024Updated 2 years ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,901Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Disaggregated serving system for Large Language Models (LLMs).☆847Apr 6, 2025Updated last year
- Efficient Triton Kernels for LLM Training☆6,704Updated this week
- how to optimize some algorithm in cuda.☆3,354Nov 2, 2026Updated 2 weeks ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,992Updated 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…☆3,607Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆5,068Apr 11, 2025Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,579Feb 20, 2026Updated 8 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,346Mar 6, 2025Updated last year
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆43,333Updated this week
- 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.
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,402Updated this week
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆755May 14, 2026Updated 6 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,231Oct 10, 2026Updated last month
- fastllm是后端无依赖的高性能大模型推理库,帮助您在大部分设备上高效推理大模型!☆5,129Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,344May 11, 2025Updated last year
- An Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.☆12,187Updated this week
- 🚀 Efficient implementations for emerging model architectures☆6,059Updated this week
Are these results useful?