OctoAI's repositories
Apple-M1-BERT
3X speedup over Apple’s TensorFlow plugin by using Apache TVM on M1
deformable-attention-kernel
TVMScript kernel for deformable attention
public-tvm-docker
Build TVM docker image for production compilation deployments
octoml-examples
A collection of test models for the OctoML AI acceleration service
mlperf-loadgen-harness
A simple Python harness to run an ONNX model in various concurrency and replication configurations against MLCommon's LoadGen to measure throughput.
mlcommons-inference
Fork of MLCommons inference repository to test TVM integration
onnx-golive
ONNX Runtime(ORT) Go Live, is a python package that automates the process of accelerating models with ONNX Runtime(ORT). It contains two parts including model conversion to ONNX with correctness checking and auto performance tuning with ORT. Users can run these two together through a single pipeline or run them independently as needed.
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
octoml-helm-charts
Repository for OctoML-affiliated Helm Charts
ci-terraform
Terraform configuration for TVM Jenkins Infrastructure
collage-core
Open deep learning compiler stack for cpu, gpu and specialized accelerators
grpc-web-client
gRPC-Web client in Rust
lacework-agent-ansible-role
An Ansible Role to install the Lacework Datacollector Agent
onnx-pb-rs
Protobuf definitions for onnx models
opentelemetry-datadog
DataDog integration with the OpenTelemetry crate, copied and adapted from opentelemetry-contrib https://github.com/open-telemetry/opentelemetry-rust/tree/master/opentelemetry-contrib.
relay-to-js
A translator from a serialized relay graph layout into a structured graph object in JavaScript/TypeScript
terraform-google-container-vm
This module simplifies deploying containers on GCE instances.
terraform-google-sql-db
Modular Cloud SQL database instance for Terraform.
terraform-google-vpn
A Terraform Module for setting up Google Cloud VPN