ModelTC / lightllm
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
☆2,911Updated this week
Alternatives and similar repositories for lightllm:
Users that are interested in lightllm are comparing it to the libraries listed below
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,426Updated 7 months ago
- FlashInfer: Kernel Library for LLM Serving☆2,078Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,946Updated last month
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,743Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,790Updated last year
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,965Updated last week
- LMDeploy is a toolkit for compressing, deploying, and serving LLMs.☆5,603Updated this week
- 📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, Flash-Attention, Paged-Attention, Parallelism, etc. 🎉🎉☆3,456Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,194Updated 4 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆10,325Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,702Updated 3 weeks ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆968Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)☆4,809Updated this week
- Tools for merging pretrained large language models.☆5,260Updated last week
- Serving multiple LoRA finetuned LLM as one☆1,028Updated 9 months ago
- A framework for few-shot evaluation of language models.☆7,848Updated this week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,031Updated 10 months ago
- Ongoing research training transformer language models at scale, including: BERT & GPT-2☆1,990Updated last week
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,362Updated last week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆2,591Updated this week
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,446Updated 11 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,758Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,339Updated 7 months ago
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆917Updated last week
- AllenAI's post-training codebase☆2,657Updated this week
- PyTorch native post-training library☆4,856Updated this week
- A curated list for Efficient Large Language Models☆1,445Updated this week
- OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, …☆4,681Updated last week
- An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)☆4,246Updated 3 weeks ago
- Fast, Flexible and Portable Structured Generation☆704Updated this week