Azure / MS-AMP
Microsoft Automatic Mixed Precision Library
☆581Updated 5 months ago
Alternatives and similar repositories for MS-AMP:
Users that are interested in MS-AMP are comparing it to the libraries listed below
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆452Updated this week
- Ring attention implementation with flash attention☆714Updated 3 weeks ago
- Zero Bubble Pipeline Parallelism☆373Updated 2 weeks ago
- Large Context Attention☆693Updated 2 months ago
- ☆310Updated 11 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆611Updated 2 weeks ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆431Updated 7 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆278Updated 2 weeks ago
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆771Updated 6 months ago
- Tutel MoE: An Optimized Mixture-of-Experts Implementation☆786Updated this week
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆361Updated 3 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆336Updated 7 months ago
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆557Updated last month
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,216Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆298Updated 8 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆415Updated 6 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆253Updated 9 months ago
- Pipeline Parallelism for PyTorch☆759Updated 7 months ago
- This repository contains the experimental PyTorch native float8 training UX☆222Updated 7 months ago
- This repository contains integer operators on GPUs for PyTorch.☆196Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆240Updated 4 months ago
- GPTQ inference Triton kernel☆298Updated last year
- Latency and Memory Analysis of Transformer Models for Training and Inference☆401Updated 2 weeks ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆597Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆1,369Updated 8 months ago
- Applied AI experiments and examples for PyTorch☆249Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆259Updated 4 months ago
- Best practice for training LLaMA models in Megatron-LM☆645Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆471Updated last year