FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆1,107Sep 4, 2024Updated last year
Alternatives and similar repositories for marlin
Users that are interested in marlin are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆848Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,962Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆769Aug 6, 2025Updated 11 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆96Sep 4, 2024Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆156Aug 21, 2025Updated 10 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,589Jul 17, 2025Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆343Jul 2, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆967Mar 29, 2026Updated 3 months ago
- Fast low-bit matmul kernels in Triton☆476Jun 30, 2026Updated 2 weeks ago
- Tile primitives for speedy kernels☆3,537Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,489Jul 11, 2026Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆523Nov 26, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,342Aug 28, 2025Updated 10 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,351May 11, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆269Jul 11, 2024Updated 2 years ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,666Jul 12, 2024Updated 2 years ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,332Mar 27, 2024Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆444Mar 5, 2026Updated 4 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆416Nov 20, 2025Updated 7 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,169Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,545Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,901Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆129Jul 13, 2024Updated 2 years ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆123Mar 6, 2024Updated 2 years ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆282Jul 16, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,221Apr 8, 2026Updated 3 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 3 weeks ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,340Mar 6, 2025Updated last year
- Perplexity GPU Kernels☆588Nov 7, 2025Updated 8 months ago
- GPTQ inference Triton kernel☆323May 18, 2023Updated 3 years ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆430Aug 13, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Serving multiple LoRA finetuned LLM as one☆1,166May 8, 2024Updated 2 years ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,430Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,080Updated this week
- ☆601Oct 29, 2024Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆948Feb 26, 2026Updated 4 months ago
- ☆65Apr 26, 2025Updated last year
- ☆210May 5, 2025Updated last year