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.
☆3,377Updated 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☆3,127Updated last month
- FlashInfer: Kernel Library for LLM Serving☆3,306Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,202Updated 2 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆4,217Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,558Updated last year
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆6,672Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,026Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,843Updated last year
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆2,099Updated 3 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,616Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,371Updated last week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,890Updated 3 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,259Updated 4 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,806Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆3,505Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,139Updated last year
- Fast, Flexible and Portable Structured Generation☆1,052Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,061Updated 2 weeks ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,438Updated last year
- Transformer related optimization, including BERT, GPT☆6,231Updated last year
- Minimalistic large language model 3D-parallelism training☆2,012Updated this week
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,555Updated last year
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,747Updated last year
- The Triton TensorRT-LLM Backend☆859Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Asy…☆7,287Updated this week
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,182Updated this week
- LLMPerf is a library for validating and benchmarking LLMs☆953Updated 7 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆809Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,070Updated last year
- A curated list for Efficient Large Language Models☆1,763Updated 3 weeks ago