microsoft / vattention
Dynamic Memory Management for Serving LLMs without PagedAttention
☆360Updated 2 weeks ago
Alternatives and similar repositories for vattention:
Users that are interested in vattention are comparing it to the libraries listed below
- A low-latency & high-throughput serving engine for LLMs☆351Updated 2 weeks ago
- Perplexity GPU Kernels☆272Updated this week
- Distributed Triton for Parallel Systems☆618Updated last week
- Efficient and easy multi-instance LLM serving☆398Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆575Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆307Updated 10 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆248Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆109Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆167Updated last week
- A large-scale simulation framework for LLM inference☆371Updated 5 months ago
- Zero Bubble Pipeline Parallelism☆386Updated 3 weeks ago
- High performance Transformer implementation in C++.☆119Updated 3 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆266Updated 11 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆248Updated 6 months ago
- ☆202Updated 9 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆346Updated 7 months ago
- A throughput-oriented high-performance serving framework for LLMs☆804Updated this week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆407Updated 2 weeks ago
- ☆314Updated last year
- Materials for learning SGLang☆396Updated last week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆205Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆302Updated 5 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆345Updated this week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆173Updated 2 weeks ago
- flash attention tutorial written in python, triton, cuda, cutlass☆341Updated 4 months ago
- ☆95Updated 5 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆656Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆262Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆304Updated this week
- Fast low-bit matmul kernels in Triton☆295Updated this week