FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆1,122Sep 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…☆852Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,127Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆770Aug 6, 2025Updated last year
- 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.☆159Aug 21, 2025Updated 11 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,608Jul 17, 2025Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆345Jul 2, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆974Mar 29, 2026Updated 4 months ago
- Tile primitives for speedy kernels☆3,613Jul 13, 2026Updated 3 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆530Nov 26, 2024Updated last year
- Fast low-bit matmul kernels in Triton☆480Updated this week
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,351May 11, 2025Updated last year
- ☆271Jul 11, 2024Updated 2 years ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,352Aug 28, 2025Updated 11 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Distributed Compiler based on Triton for Parallel Systems☆1,509Updated this week
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,674Jul 12, 2024Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆450Mar 5, 2026Updated 5 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,347Mar 27, 2024Updated 2 years ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆425Nov 20, 2025Updated 8 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,212Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,414Updated this week
- Perplexity GPU Kernels☆598Nov 7, 2025Updated 9 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆394Apr 13, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,482Updated this week
- A Quirky Assortment of CuTe Kernels☆1,094Updated this week
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆129Jul 13, 2024Updated 2 years ago
- PyTorch native quantization and sparsity for training and inference☆2,933Updated this week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated last month
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,225Apr 8, 2026Updated 4 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆281Jul 16, 2025Updated last year
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆3,636Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,340Mar 6, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆431Aug 13, 2024Updated last year
- GPTQ inference Triton kernel☆322May 18, 2023Updated 3 years ago
- Serving multiple LoRA finetuned LLM as one☆1,170May 8, 2024Updated 2 years ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆123Mar 6, 2024Updated 2 years ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,210Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆953Feb 26, 2026Updated 5 months ago
- ☆605Oct 29, 2024Updated last year