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.
☆3,683Updated 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☆3,324Updated 3 months ago
- FlashInfer: Kernel Library for LLM Serving☆3,982Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,260Updated 5 months ago
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆7,199Updated this week
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,635Updated 2 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,650Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,178Updated 2 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,149Updated this week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,864Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆4,168Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,008Updated 2 weeks ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,070Updated 4 months ago
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,977Updated 6 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,143Updated last month
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,209Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,291Updated 7 months ago
- LLMPerf is a library for validating and benchmarking LLMs☆1,036Updated 10 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,839Updated last week
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Bla…☆2,860Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,536Updated last year
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆11,955Updated this week
- Fast, Flexible and Portable Structured Generation☆1,323Updated last week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,395Updated last week
- The Triton TensorRT-LLM Backend☆903Updated this week
- Transformer related optimization, including BERT, GPT☆6,331Updated last year
- Fast inference from large lauguage models via speculative decoding☆841Updated last year
- A curated list for Efficient Large Language Models☆1,885Updated 4 months ago
- Minimalistic large language model 3D-parallelism training☆2,274Updated last month
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆903Updated this week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆1,884Updated last week