microsoft / T-MACLinks
Low-bit LLM inference on CPU/NPU with lookup table
☆912Updated 7 months ago
Alternatives and similar repositories for T-MAC
Users that are interested in T-MAC are comparing it to the libraries listed below
Sorting:
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆743Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆802Updated 10 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆987Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆937Updated 2 months ago
- ☆436Updated 4 months ago
- 🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality degradation across Weight-Only Quantiza…☆815Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆673Updated 8 months ago
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆982Updated this week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,174Updated 3 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆611Updated last year
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.☆664Updated 2 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,224Updated 4 months ago
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆274Updated 5 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,021Updated this week
- Official implementation of Half-Quadratic Quantization (HQQ)☆905Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆457Updated 7 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆871Updated last week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆885Updated last month
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆219Updated last week
- ☆520Updated 2 weeks ago
- A high-performance inference system for large language models, designed for production environments.☆490Updated last month
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,084Updated last week
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆370Updated 11 months ago
- Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O☆547Updated 4 months ago
- High-speed and easy-use LLM serving framework for local deployment☆141Updated 5 months ago
- llm-export can export llm model to onnx.☆340Updated 2 months ago
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆326Updated last month
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 6 months ago
- This repository is a read-only mirror of https://gitlab.arm.com/kleidi/kleidiai☆111Updated this week
- The Triton TensorRT-LLM Backend☆914Updated last week