IST-DASLab / marlinLinks
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆982Updated 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…☆801Updated 10 months ago
- A throughput-oriented high-performance serving framework for LLMs☆936Updated 2 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆741Updated 5 months ago
- Microsoft Automatic Mixed Precision Library☆635Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆397Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆454Updated 7 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆472Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆905Updated 3 weeks ago
- ☆576Updated last year
- A low-latency & high-throughput serving engine for LLMs☆464Updated last week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆475Updated 8 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,171Updated 3 months ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,314Updated 10 months ago
- ☆206Updated 8 months ago
- Serving multiple LoRA finetuned LLM as one☆1,131Updated last year
- Fast low-bit matmul kernels in Triton☆418Updated 3 weeks ago
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,585Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆605Updated last year
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆971Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆333Updated last year
- Perplexity GPU Kernels☆552Updated 2 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆626Updated this week
- Applied AI experiments and examples for PyTorch☆312Updated 4 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆885Updated last month
- Zero Bubble Pipeline Parallelism☆445Updated 8 months ago
- ☆352Updated last year
- Materials for learning SGLang☆714Updated last week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆233Updated this week
- 🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…☆806Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 5 months ago