atomicapple0 / libsmctrlLinks
Artifact from "Hardware Compute Partitioning on NVIDIA GPUs". THIS IS A FORK OF BAKITAS REPO
☆29Updated last year
Alternatives and similar repositories for libsmctrl
Users that are interested in libsmctrl are comparing it to the libraries listed below
Sorting:
- ☆79Updated 2 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- LLM serving cluster simulator☆106Updated last year
- ☆23Updated 2 years ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- ☆117Updated last month
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches☆73Updated last year
- ☆73Updated 2 months ago
- ☆29Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- An interference-aware scheduler for fine-grained GPU sharing☆140Updated 4 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆94Updated 2 years ago
- ☆77Updated last month
- ☆22Updated last year
- A lightweight design for computation-communication overlap.☆143Updated this week
- ☆103Updated 7 months ago
- [ACM EuroSys '23] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆56Updated last year
- LLM Inference analyzer for different hardware platforms☆73Updated 3 weeks ago
- Microsoft Collective Communication Library☆64Updated 7 months ago
- ☆28Updated 11 months ago
- ☆90Updated 5 months ago
- ☆122Updated 6 months ago
- ☆42Updated this week
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- ☆13Updated 11 months ago
- ☆37Updated 3 years ago
- This repository is established to store personal notes and annotated papers during daily research.☆128Updated this week
- NCCL Profiling Kit☆138Updated 11 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆177Updated 8 months ago