FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆1,061Sep 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…☆834Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,498Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆760Aug 6, 2025Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆95Sep 4, 2024Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,512Jul 17, 2025Updated 9 months ago
- 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.
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆154Aug 21, 2025Updated 8 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆337Jul 2, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆954Mar 29, 2026Updated last month
- Fast low-bit matmul kernels in Triton☆445Updated this week
- Tile primitives for speedy kernels☆3,326Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,414Apr 22, 2026Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆505Nov 26, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,295Aug 28, 2025Updated 8 months ago
- ☆264Jul 11, 2024Updated 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.
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,331May 11, 2025Updated 11 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,641Jul 12, 2024Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,293Mar 27, 2024Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆428Mar 5, 2026Updated last month
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,025Updated this week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆387Nov 20, 2025Updated 5 months ago
- 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☆3,137Apr 21, 2026Updated last week
- PyTorch native quantization and sparsity for training and inference☆2,796Updated this week
- 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.
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆128Jul 13, 2024Updated last year
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆97Feb 20, 2026Updated 2 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,207Apr 8, 2026Updated 3 weeks ago
- Perplexity GPU Kernels☆569Nov 7, 2025Updated 5 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,332Mar 6, 2025Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆280Jul 16, 2025Updated 9 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆121Mar 6, 2024Updated 2 years ago
- GPTQ inference Triton kernel☆321May 18, 2023Updated 2 years ago
- Serving multiple LoRA finetuned LLM as one☆1,155May 8, 2024Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,291Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆418Aug 13, 2024Updated last year
- ☆590Oct 29, 2024Updated last year
- ☆67Apr 26, 2025Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆931Feb 26, 2026Updated 2 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,638Updated this week
- ☆210May 5, 2025Updated 11 months ago