IST-DASLab / marlinLinks
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
☆895Updated 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…☆753Updated 6 months ago
- A throughput-oriented high-performance serving framework for LLMs☆887Updated last month
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆667Updated last month
- Serving multiple LoRA finetuned LLM as one☆1,086Updated last year
- ☆555Updated 10 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆414Updated 3 months ago
- Microsoft Automatic Mixed Precision Library☆619Updated 11 months ago
- ☆197Updated 4 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆422Updated 9 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆377Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,496Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆879Updated last week
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆778Updated this week
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,276Updated 6 months ago
- GPTQ inference Triton kernel☆307Updated 2 years ago
- Fast low-bit matmul kernels in Triton☆365Updated this week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆450Updated 4 months ago
- Zero Bubble Pipeline Parallelism☆424Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU.☆614Updated this week
- A low-latency & high-throughput serving engine for LLMs☆412Updated 3 months ago
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆847Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆263Updated last month
- Materials for learning SGLang☆572Updated 2 weeks ago
- Perplexity GPU Kernels☆458Updated last month
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,124Updated last month
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆704Updated last year
- Disaggregated serving system for Large Language Models (LLMs).☆685Updated 5 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆547Updated last year
- ☆335Updated last year