microsoft / vattentionLinks
Dynamic Memory Management for Serving LLMs without PagedAttention
☆444Updated 6 months ago
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☆450Updated last month
- Perplexity GPU Kernels☆531Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆512Updated 2 months ago
- Allow torch tensor memory to be released and resumed later☆177Updated this week
- ☆324Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆188Updated last month
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆282Updated 8 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆466Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆437Updated 6 months ago
- High performance Transformer implementation in C++.☆142Updated 10 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆437Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆262Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆224Updated 2 years ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆786Updated 8 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆737Updated 7 months ago
- nnScaler: Compiling DNN models for Parallel Training☆120Updated 2 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆292Updated 5 months ago
- A large-scale simulation framework for LLM inference☆488Updated 4 months ago
- ☆246Updated last year
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆581Updated last year
- ☆124Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆498Updated this week
- A collection of memory efficient attention operators implemented in the Triton language.☆283Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆272Updated 4 months ago
- ☆147Updated 11 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆454Updated 6 months ago
- A Easy-to-understand TensorOp Matmul Tutorial☆394Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- A throughput-oriented high-performance serving framework for LLMs☆918Updated last month
- ☆79Updated last month