microsoft / vattention
Dynamic Memory Management for Serving LLMs without PagedAttention
☆345Updated 3 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☆337Updated 2 months ago
- Distributed Triton for Parallel Systems☆372Updated this week
- Efficient and easy multi-instance LLM serving☆367Updated 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…☆242Updated last month
- A large-scale simulation framework for LLM inference☆359Updated 4 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆262Updated 10 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆303Updated 9 months ago
- ☆197Updated 9 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆435Updated 7 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆550Updated last week
- A Easy-to-understand TensorOp Matmul Tutorial☆340Updated 6 months ago
- Applied AI experiments and examples for PyTorch☆256Updated 3 weeks ago
- Materials for learning SGLang☆371Updated 3 weeks ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆403Updated last month
- High performance Transformer implementation in C++.☆115Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆204Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆276Updated 4 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆330Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆156Updated 9 months ago
- Fast low-bit matmul kernels in Triton☆285Updated this week
- Perplexity GPU Kernels☆185Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆165Updated 2 weeks ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆247Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆106Updated 2 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆325Updated 3 months ago
- Zero Bubble Pipeline Parallelism☆381Updated last week
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆635Updated last month
- ☆94Updated 5 months ago
- ☆91Updated 7 months ago
- A throughput-oriented high-performance serving framework for LLMs☆794Updated 6 months ago