AI-HPC-Research-Team / AIPerfLinks
Automated machine learning as an AI-HPC benchmark
☆65Updated 2 years ago
Alternatives and similar repositories for AIPerf
Users that are interested in AIPerf are comparing it to the libraries listed below
Sorting:
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆90Updated last month
- NCCL Profiling Kit☆139Updated last year
- Synthesizer for optimal collective communication algorithms☆108Updated last year
- Fine-grained GPU sharing primitives☆142Updated 5 years ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆249Updated last week
- NCCL Examples from Official NVIDIA NCCL Developer Guide.☆17Updated 7 years ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- An Efficient Pipelined Data Parallel Approach for Training Large Model☆77Updated 4 years ago
- An unofficial cuda assembler, for all generations of SASS, hopefully :)☆83Updated 2 years ago
- ☆58Updated 4 years ago
- GVProf: A Value Profiler for GPU-based Clusters☆51Updated last year
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆121Updated 3 years ago
- A home for the final text of all TVM RFCs.☆105Updated 9 months ago
- ☆79Updated 2 years ago
- RDMA and SHARP plugins for nccl library☆197Updated 2 weeks ago
- ☆23Updated 3 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- ☆149Updated 5 months ago
- GPU-scheduler-for-deep-learning☆208Updated 4 years ago
- ☆74Updated 3 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆117Updated last year
- DeepSeek-V3/R1 inference performance simulator☆151Updated 3 months ago
- PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications☆126Updated 3 years ago
- ☆28Updated last year
- ☆100Updated last year
- ☆37Updated 6 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆52Updated 10 months ago
- Repository for SysML19 Artifacts Evaluation☆54Updated 6 years ago
- [MLSys 2021] IOS: Inter-Operator Scheduler for CNN Acceleration☆200Updated 3 years ago
- Thunder Research Group's Collective Communication Library☆37Updated last year