FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆1,041Sep 4, 2024Updated last year
Alternatives and similar repositories for marlin
Users that are interested in marlin are comparing it to the libraries listed below
Sorting:
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆818Mar 6, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆5,145Updated this week
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆752Aug 6, 2025Updated 7 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆94Sep 4, 2024Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,463Jul 17, 2025Updated 8 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆155Aug 21, 2025Updated 6 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Jul 2, 2024Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆949Oct 29, 2025Updated 4 months ago
- Fast low-bit matmul kernels in Triton☆438Feb 1, 2026Updated last month
- Tile primitives for speedy kernels☆3,232Updated this week
- Distributed Compiler based on Triton for Parallel Systems☆1,386Mar 11, 2026Updated last week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆489Nov 26, 2024Updated last year
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,273Aug 28, 2025Updated 6 months ago
- ☆261Jul 11, 2024Updated last year
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,317May 11, 2025Updated 10 months ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,621Jul 12, 2024Updated last year
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,264Mar 27, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆359Nov 20, 2025Updated 3 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,945Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆409Mar 5, 2026Updated 2 weeks ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆389Apr 13, 2025Updated 11 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆2,891Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,730Updated this week
- 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☆95Feb 20, 2026Updated 3 weeks ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,196Mar 9, 2026Updated last week
- Perplexity GPU Kernels☆566Nov 7, 2025Updated 4 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,322Mar 6, 2025Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Jul 16, 2025Updated 8 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆120Mar 6, 2024Updated 2 years ago
- GPTQ inference Triton kernel☆321May 18, 2023Updated 2 years ago
- Serving multiple LoRA finetuned LLM as one☆1,148May 8, 2024Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆408Aug 13, 2024Updated last year
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,211Updated this week
- ☆580Oct 29, 2024Updated last year
- ☆65Apr 26, 2025Updated 10 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆919Feb 26, 2026Updated 3 weeks ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,442Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,156Mar 12, 2026Updated last week