microsoft / T-MACLinks
Low-bit LLM inference on CPU/NPU with lookup table
☆898Updated 6 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.☆723Updated 4 months ago
- ☆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…☆790Updated 9 months ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆958Updated 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
- A throughput-oriented high-performance serving framework for LLMs☆921Updated last month
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆668Updated 7 months ago
- Advanced quantization toolkit for LLMs and VLMs. Native support for WOQ, MXFP4, NVFP4, GGUF, Adaptive Schemes and seamless integration wi…☆753Updated this week
- [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
- [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLM, VLM, and video generation models.☆640Updated 3 weeks ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆589Updated last year
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆270Updated 4 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,188Updated 3 months ago
- A high-performance inference system for large language models, designed for production environments.☆487Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆446Updated 6 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆940Updated this week
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆881Updated 2 weeks ago
- High-speed and easy-use LLM serving framework for local deployment☆137Updated 4 months ago
- FlagGems is an operator library for large language models implemented in the Triton Language.☆783Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆523Updated last week
- An innovative library for efficient LLM inference via low-bit quantization☆350Updated last year
- ☆515Updated 3 weeks ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆1,981Updated this week
- TinyChatEngine: On-Device LLM Inference Library☆931Updated last year
- A framework for efficient model inference with omni-modality models☆766Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆747Updated 8 months ago
- [ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆227Updated 10 months ago
- Materials for learning SGLang☆667Updated last week
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆206Updated 2 months ago
- Efficient LLM Inference over Long Sequences☆392Updated 5 months ago