microsoft / T-MACLinks
Low-bit LLM inference on CPU/NPU with lookup table
☆887Updated 5 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:
- ☆431Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆778Updated 8 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆946Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆709Updated 3 months ago
- LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU vi…☆876Updated last week
- Advanced quantization toolkit for LLMs. Native support for WOQ, MXFP4, NVFP4, GGUF, Adaptive Bits and seamless integration with Transform…☆712Updated this week
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆666Updated 6 months ago
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆622Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆914Updated 3 weeks ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆575Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,148Updated last month
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,167Updated 2 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆926Updated this week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆872Updated 5 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆757Updated this week
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆268Updated 3 months ago
- High-speed and easy-use LLM serving framework for local deployment☆134Updated 3 months ago
- A high-performance inference system for large language models, designed for production environments.☆482Updated last week
- TinyChatEngine: On-Device LLM Inference Library☆923Updated last year
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,951Updated this week
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆454Updated this week
- FlashInfer: Kernel Library for LLM Serving☆4,062Updated this week
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆478Updated last year
- ☆512Updated 2 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆434Updated 5 months ago
- Fast, Flexible and Portable Structured Generation☆1,375Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆729Updated 7 months ago
- LLaMa/RWKV onnx models, quantization and testcase☆367Updated 2 years ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆891Updated 3 weeks ago
- Distributed Compiler based on Triton for Parallel Systems☆1,233Updated this week