microsoft / vattentionLinks
Dynamic Memory Management for Serving LLMs without PagedAttention
☆401Updated last month
Alternatives and similar repositories for vattention
Users that are interested in vattention are comparing it to the libraries listed below
Sorting:
- A low-latency & high-throughput serving engine for LLMs☆388Updated last month
- Perplexity GPU Kernels☆395Updated last month
- Efficient and easy multi-instance LLM serving☆445Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆639Updated 3 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆207Updated this week
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- A large-scale simulation framework for LLM inference☆403Updated 2 weeks ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆434Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆113Updated this week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆714Updated 4 months ago
- Materials for learning SGLang☆475Updated this week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆256Updated 4 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆216Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆870Updated last week
- Zero Bubble Pipeline Parallelism☆403Updated 2 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆506Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆313Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆835Updated last month
- A collection of memory efficient attention operators implemented in the Triton language.☆272Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆254Updated 8 months ago
- A lightweight design for computation-communication overlap.☆146Updated 3 weeks ago
- ☆106Updated 8 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆385Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆230Updated last month
- flash attention tutorial written in python, triton, cuda, cutlass☆380Updated last month
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆58Updated 11 months ago
- ☆330Updated last year
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆161Updated this week
- ☆214Updated last year
- Applied AI experiments and examples for PyTorch☆281Updated last month