A safetensors extension to efficiently store sparse quantized tensors on disk
☆289Jun 6, 2026Updated this week
Alternatives and similar repositories for compressed-tensors
Users that are interested in compressed-tensors are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,335Updated this week
- ☆210May 5, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,082Sep 4, 2024Updated last year
- Fast low-bit matmul kernels in Triton☆467May 15, 2026Updated 3 weeks ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Dec 4, 2025Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Boosting 4-bit inference kernels with 2:4 Sparsity☆96Sep 4, 2024Updated last year
- ☆90Jan 23, 2025Updated last year
- A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM☆502Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- A pytorch quantization backend for optimum☆1,042Updated this week
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆278Oct 3, 2025Updated 8 months ago
- ☆22May 5, 2025Updated last year
- PyTorch native quantization and sparsity for training and inference☆2,847Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆513Nov 26, 2024Updated last year
- Applied AI experiments and examples for PyTorch☆323Aug 22, 2025Updated 9 months ago
- LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM…☆1,169Updated this week
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆47Jun 11, 2025Updated 11 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆43Jan 15, 2024Updated 2 years ago
- ☆115Apr 19, 2024Updated 2 years ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,341May 11, 2025Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆425Aug 13, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,760Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆402Nov 20, 2025Updated 6 months ago
- extensible collectives library in triton☆98Mar 31, 2025Updated last year
- ☆14Jul 13, 2025Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆341Jul 2, 2024Updated last year
- ICML2017 MEC: Memory-efficient Convolution for Deep Neural Network C++实现(非官方)☆17Apr 9, 2019Updated 7 years ago
- Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.☆74Sep 8, 2024Updated last year
- A curated collection of resources, tutorials, and best practices for learning and mastering NVIDIA CUTLASS☆261May 6, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆155Aug 21, 2025Updated 9 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆841Mar 6, 2025Updated last year
- A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative…☆2,891Updated this week
- ☆166Feb 15, 2025Updated last year
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆185Nov 11, 2025Updated 6 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆940Feb 26, 2026Updated 3 months ago
- MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI tr…☆107Jun 1, 2026Updated last week