microsoft / vattentionLinks
Dynamic Memory Management for Serving LLMs without PagedAttention
☆457Updated 8 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☆470Updated 3 weeks ago
- Perplexity GPU Kernels☆554Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆449Updated 8 months ago
- Efficient and easy multi-instance LLM serving☆523Updated 4 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆278Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆772Updated 9 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…☆283Updated 10 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆233Updated 2 years ago
- ☆342Updated this week
- Latency and Memory Analysis of Transformer Models for Training and Inference☆479Updated 9 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆312Updated 7 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆807Updated 10 months ago
- Allow torch tensor memory to be released and resumed later☆213Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆213Updated last week
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆612Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆335Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆659Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 6 months ago
- A throughput-oriented high-performance serving framework for LLMs☆943Updated 3 months ago
- High performance Transformer implementation in C++.☆148Updated last year
- A large-scale simulation framework for LLM inference☆528Updated 6 months ago
- nnScaler: Compiling DNN models for Parallel Training☆124Updated 4 months ago
- Materials for learning SGLang☆728Updated 3 weeks ago
- A collection of memory efficient attention operators implemented in the Triton language.☆287Updated last year
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆455Updated this week
- ☆258Updated last year
- ☆130Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆483Updated last week
- ☆158Updated last year
- Applied AI experiments and examples for PyTorch☆314Updated 5 months ago