microsoft / vattentionLinks
Dynamic Memory Management for Serving LLMs without PagedAttention
☆410Updated 3 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☆412Updated 3 months ago
- Perplexity GPU Kernels☆451Updated last month
- Efficient and easy multi-instance LLM serving☆480Updated last week
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆268Updated 6 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆747Updated 6 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆685Updated 5 months ago
- A large-scale simulation framework for LLM inference☆431Updated last month
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆355Updated last week
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆219Updated last year
- High performance Transformer implementation in C++.☆132Updated 7 months ago
- Latency and Memory Analysis of Transformer Models for Training and Inference☆450Updated 4 months ago
- Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline mod…☆546Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆231Updated 2 months ago
- Zero Bubble Pipeline Parallelism☆424Updated 4 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆412Updated last week
- A lightweight design for computation-communication overlap.☆161Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆886Updated last month
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆205Updated last week
- Allow torch tensor memory to be released and resumed later☆126Updated 2 weeks ago
- ☆290Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆259Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆263Updated last month
- ☆120Updated 10 months ago
- ☆230Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆376Updated 11 months ago
- Ultra and Unified CCL☆530Updated this week
- Materials for learning SGLang☆562Updated last week
- flash attention tutorial written in python, triton, cuda, cutlass☆416Updated 3 months ago