vllm-project / llm-compressor
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
☆894Updated this week
Alternatives and similar repositories for llm-compressor:
Users that are interested in llm-compressor are comparing it to the libraries listed below
- [NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which r…☆890Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆714Updated 4 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆689Updated 4 months ago
- Minimalistic large language model 3D-parallelism training☆1,400Updated this week
- Efficient, Flexible and Portable Structured Generation☆619Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆737Updated 2 weeks ago
- Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)☆928Updated 3 weeks ago
- LLMPerf is a library for validating and benchmarking LLMs☆709Updated last month
- An Open Source Toolkit For LLM Distillation☆442Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆1,876Updated this week
- Serving multiple LoRA finetuned LLM as one☆1,018Updated 8 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆492Updated this week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,022Updated this week
- Advanced Quantization Algorithm for LLMs/VLMs.☆362Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆257Updated 3 months ago
- Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.☆229Updated this week
- For releasing code related to compression methods for transformers, accompanying our publications☆405Updated last week
- Efficient LLM Inference over Long Sequences☆349Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,183Updated 3 months ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆572Updated last week
- A family of compressed models obtained via pruning and knowledge distillation☆315Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆1,911Updated last week
- Making Long-Context LLM Inference 10x Faster and 10x Cheaper☆401Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆694Updated 4 months ago
- Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs☆184Updated last month
- Scalable toolkit for efficient model alignment☆693Updated this week
- An innovative library for efficient LLM inference via low-bit quantization☆352Updated 4 months ago
- ☆497Updated 5 months ago
- Comparison of Language Model Inference Engines☆203Updated last month
- LLM KV cache compression made easy☆356Updated this week