FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆1,153Sep 4, 2024Updated 2 years ago
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…☆862Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,556Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆771Aug 6, 2025Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆101Sep 4, 2024Updated 2 years ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆160Aug 21, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,649Jul 17, 2025Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆348Jul 2, 2024Updated 2 years ago
- A throughput-oriented high-performance serving framework for LLMs☆975Mar 29, 2026Updated 6 months ago
- Tile primitives for speedy kernels☆3,745Sep 12, 2026Updated 3 weeks ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆534Nov 26, 2024Updated last year
- Fast low-bit matmul kernels in Triton☆488Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,557Sep 18, 2026Updated 2 weeks ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,346May 11, 2025Updated last year
- ☆272Jul 11, 2024Updated 2 years ago
- 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 fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,368Aug 28, 2025Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,694Jul 12, 2024Updated 2 years ago
- A Easy-to-understand TensorOp Matmul Tutorial☆453Mar 5, 2026Updated 7 months ago
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,381Mar 27, 2024Updated 2 years ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆434Nov 20, 2025Updated 10 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,305Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,540Updated this week
- Perplexity GPU Kernels☆606Nov 7, 2025Updated 11 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆395Apr 13, 2025Updated 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…☆3,569Updated this week
- A Quirky Assortment of CuTe Kernels☆1,166Sep 17, 2026Updated 2 weeks ago
- PyTorch native quantization for training and inference☆2,993Updated this week
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆96Jun 21, 2026Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆281Jul 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…☆1,228Sep 10, 2026Updated 3 weeks ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆130Jul 13, 2024Updated 2 years ago
- State-of-the-art LLM compression, built for production inference with vLLM☆3,855Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,342Mar 6, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆436Aug 13, 2024Updated 2 years ago
- GPTQ inference Triton kernel☆322May 18, 2023Updated 3 years ago
- Serving multiple LoRA finetuned LLM as one☆1,175May 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☆10,542Sep 23, 2026Updated 2 weeks ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆959Feb 26, 2026Updated 7 months ago
- ☆609Oct 29, 2024Updated last year