IST-DASLab / marlinLinks
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆958Updated 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…☆786Updated 9 months ago
- A throughput-oriented high-performance serving framework for LLMs☆918Updated last month
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆720Updated 3 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆446Updated 6 months ago
- Microsoft Automatic Mixed Precision Library☆628Updated this week
- ☆570Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆466Updated 7 months ago
- Serving multiple LoRA finetuned LLM as one☆1,121Updated last year
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆461Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆391Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,568Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,163Updated 2 months ago
- ☆205Updated 7 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆894Updated last month
- GPTQ inference Triton kernel☆315Updated 2 years ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆272Updated 4 months ago
- A low-latency & high-throughput serving engine for LLMs☆450Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,307Updated 9 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆589Updated last year
- Zero Bubble Pipeline Parallelism☆437Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆523Updated this week
- Fast low-bit matmul kernels in Triton☆401Updated 2 weeks ago
- Applied AI experiments and examples for PyTorch☆308Updated 3 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆875Updated last week
- Ring attention implementation with flash attention☆923Updated 2 months ago
- Materials for learning SGLang☆658Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- ☆348Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆710Updated last year
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆913Updated this week