awslabs / nki-autotuneLinks
☆14Updated last week
Alternatives and similar repositories for nki-autotune
Users that are interested in nki-autotune are comparing it to the libraries listed below
Sorting:
- ☆37Updated 3 weeks ago
- Project showing how to develop NKI kernels for Llama 3.2 1B inference☆14Updated 3 weeks ago
- ☆58Updated last month
- ☆17Updated last month
- ☆38Updated 6 months ago
- Example code for AWS Neuron SDK developers building inference and training applications☆149Updated 2 weeks ago
- ☆11Updated last month
- ☆14Updated 7 months ago
- SageMaker Studio Docker CLI Extension☆13Updated last year
- ☆24Updated last year
- Run FMBench simultaneously across multiple Amazon EC2 machines to benchmark an FM across multiple serving stacks simultaneously☆15Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆18Updated this week
- ☆47Updated last month
- ☆12Updated 8 months ago
- ☆41Updated last month
- ☆27Updated 2 months ago
- Collection of best practices, reference architectures, model training examples and utilities to train large models on AWS.☆313Updated this week
- ☆53Updated 3 weeks ago
- ☆10Updated 4 months ago
- EFA/NCCL base AMI build Packer and CodeBuild/Pipeline files. Also base Docker build files to enable EFA/NCCL in containers☆43Updated last year
- ☆23Updated 3 months ago
- Foundation model benchmarking tool. Run any model on any AWS platform and benchmark for performance across instance type and serving stac…☆246Updated 2 months ago
- ☆110Updated 5 months ago
- Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.☆230Updated this week
- ☆105Updated this week
- ☆18Updated last year
- FM-Leaderboard-er allows you to create leaderboard to find the best LLM/prompt for your own business use case based on your data, task, p…☆18Updated 7 months ago
- Notebooks and sample code for Build On Trainium☆16Updated last week
- A2RL is a Python library for offline reinforcement learning☆36Updated 9 months ago
- ☆14Updated 4 years ago