OctoML (@octoml)
Guthub

octoml

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

Apple-M1-BERT

3X speedup over Appleโ€™s TensorFlow plugin by using Apache TVM on M1
Python
135
star
2

octoml-profile

Home for OctoML PyTorch Profiler
104
star
3

synr

A library for syntactically rewriting Python programs, pronounced (sinner).
Python
70
star
4

octoai-textgen-cookbook

Simple getting-started code examples for LLM applications powered by OctoAI
Python
37
star
5

deformable-attention-kernel

TVMScript kernel for deformable attention
Python
24
star
6

triton-client-rs

A client library in Rust for Nvidia Triton.
Rust
23
star
7

octoml-llm-qa

A code sample that shows how to use ๐Ÿฆœ๏ธ๐Ÿ”—langchain, ๐Ÿฆ™llama_index and a hosted LLM endpoint to do a standard chat or Q&A about a pdf document
Python
17
star
8

relax

A fork of tvm/unity
Python
15
star
9

tvm2onnx

An open-source tool created by OctoML that converts TVM-optimized models to code runnable in ONNX Runtime.
Python
14
star
10

octoml-cli-tutorials

A repository containing full end to end examples of the OctoML CLI workflow.
Python
14
star
11

TransparentAI

An example of building your own ML cloud app using OctoML.
Python
13
star
12

public-tvm-docker

Build TVM docker image for production compilation deployments
13
star
13

dockercon23-octoai

DockerCon 2023 OctoAI AI/ML Workshop GitHub Repo
Jupyter Notebook
8
star
14

qualcomm

C
8
star
15

tvm-build

A library for building TVM programmatically.
Rust
7
star
16

mlops

CK MLOps components
6
star
17

octoml-examples

A collection of test models for the OctoML AI acceleration service
5
star
18

octoai-apps

A collection of OctoAI-based demos.
TypeScript
5
star
19

macho-dyld

Custom dyld version inherited from original Apple dyld implementation
C++
4
star
20

cm-mlops

Collective Mind repository with unified automations to automatically co-design, optimize and deploy intelligent and Pareto-efficient systems across continuously changing software and hardware stacks.
Python
4
star
21

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.
Python
4
star
22

octoai-template-apps

Python
3
star
23

fern-config

Configuration for generating SDKs and Documentation.
MDX
3
star
24

mlcommons-inference

Fork of MLCommons inference repository to test TVM integration
Python
2
star
25

azsphere

TVM on Azure Sphere Platform
C
2
star
26

venv

CK virtual environment
Python
2
star
27

octoai-launch-examples

Examples of how to build Generative AI applications powered by the OctoAI compute service.
Jupyter Notebook
1
star
28

octocloud-templates

Python
1
star
29

.github

1
star