vllm-project / llm-compressorLinks
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
☆2,447Updated last week
Alternatives and similar repositories for llm-compressor
Users that are interested in llm-compressor are comparing it to the libraries listed below
Sorting:
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆943Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,354Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,300Updated 7 months ago
- Minimalistic large language model 3D-parallelism training☆2,381Updated 2 weeks ago
- Fast, Flexible and Portable Structured Generation☆1,428Updated last week
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,399Updated 5 months ago
- Advanced quantization toolkit for LLMs and VLMs. Support for WOQ, MXFP4, NVFP4, GGUF, Adaptive Schemes and seamless integration with Tra…☆775Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,169Updated 2 months ago
- The Triton TensorRT-LLM Backend☆909Updated last week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆2,212Updated last week
- LLMPerf is a library for validating and benchmarking LLMs☆1,068Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆924Updated last month
- Official implementation of Half-Quadratic Quantization (HQQ)☆902Updated last week
- Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs☆765Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,804Updated this week
- vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization☆2,050Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,591Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,078Updated last week
- A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresse…☆1,720Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆962Updated last year
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,882Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,126Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,310Updated 9 months ago
- An Open Source Toolkit For LLM Distillation☆810Updated last week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,085Updated 5 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,680Updated last year
- Scalable data pre processing and curation toolkit for LLMs☆1,288Updated this week
- A pytorch quantization backend for optimum☆1,019Updated last month
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆670Updated 8 months ago
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,995Updated this week