mit-han-lab / smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
☆1,369Updated 8 months ago
Alternatives and similar repositories for smoothquant:
Users that are interested in smoothquant are comparing it to the libraries listed below
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,063Updated 11 months ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,861Updated this week
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,057Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆771Updated 6 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,216Updated 2 weeks ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆789Updated 5 months ago
- Microsoft Automatic Mixed Precision Library☆581Updated 5 months ago
- FlashInfer: Kernel Library for LLM Serving☆2,439Updated this week
- Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".☆775Updated 7 months ago
- A simple and effective LLM pruning approach.☆723Updated 7 months ago
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆680Updated 7 months ago
- [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baich…☆979Updated 5 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs…☆2,293Updated this week
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆278Updated 2 weeks ago
- Serving multiple LoRA finetuned LLM as one☆1,040Updated 10 months ago
- Tutel MoE: An Optimized Mixture-of-Experts Implementation☆786Updated this week
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆1,990Updated this week
- A pytorch quantization backend for optimum☆902Updated 2 weeks ago
- Fast inference from large lauguage models via speculative decoding☆692Updated 7 months ago
- Awesome LLM compression research papers and tools.☆1,427Updated this week
- ☆310Updated 11 months ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,466Updated 8 months ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,773Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆597Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,021Updated 2 weeks ago
- Automatically split your PyTorch models on multiple GPUs for training & inference☆650Updated last year
- For releasing code related to compression methods for transformers, accompanying our publications☆416Updated 2 months ago
- ☆542Updated 3 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆361Updated 3 months ago