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.
☆3,730Updated 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☆3,347Updated 4 months ago
- FlashInfer: Kernel Library for LLM Serving☆4,099Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,269Updated 6 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,660Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,265Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,713Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,074Updated 4 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,238Updated this week
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,193Updated 3 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,868Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,283Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,989Updated 7 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆2,925Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,152Updated last month
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,219Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,302Updated 8 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,840Updated this week
- Fast, Flexible and Portable Structured Generation☆1,375Updated last week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,003Updated last week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,550Updated last year
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,429Updated last week
- Minimalistic large language model 3D-parallelism training☆2,323Updated 2 months ago
- Transformer related optimization, including BERT, GPT☆6,348Updated last year
- YaRN: Efficient Context Window Extension of Large Language Models☆1,637Updated last year
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆886Updated this week
- The Triton TensorRT-LLM Backend☆906Updated this week
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆6,295Updated last week
- slime is an LLM post-training framework for RL Scaling.☆2,480Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆926Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆914Updated 3 weeks ago