ModelTC / LightLLMLinks
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
☆3,440Updated this week
Alternatives and similar repositories for LightLLM
Users that are interested in LightLLM are comparing it to the libraries listed below
Sorting:
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,189Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆3,474Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,225Updated 2 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,587Updated last year
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,446Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,845Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,832Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,044Updated last month
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,350Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,126Updated 3 weeks ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,700Updated this week
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,726Updated last week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,086Updated this week
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,813Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,911Updated 3 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,602Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,263Updated 5 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,155Updated last year
- Minimalistic large language model 3D-parallelism training☆2,101Updated 3 weeks ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,469Updated last year
- LLMPerf is a library for validating and benchmarking LLMs☆975Updated 8 months ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,269Updated last week
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,571Updated last year
- Transformer related optimization, including BERT, GPT☆6,267Updated last year
- A curated list for Efficient Large Language Models☆1,809Updated last month
- The Triton TensorRT-LLM Backend☆875Updated this week
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆5,810Updated this week
- Fast, Flexible and Portable Structured Generation☆1,131Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,082Updated last year
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆830Updated last week