SHARK

Communication Channels

• GitHub issues: Feature requests, bugs etc
• Nod.ai SHARK Discord server: Real time discussions with the nod.ai team and other users

Installation

Check out the code

git clone https://github.com/NodLabs/dSHARK.git 

Setup your Python VirtualEnvironment and Dependencies

# Setup venv and install necessary packages (torch-mlir, nodLabs/Shark, ...).
./setup_venv.sh
# Please activate the venv after installation.

Run a demo script

python -m  shark.examples.resnet50_script --device="cpu" # Use gpu | vulkan

Run all tests on CPU/GPU/VULKAN

pytest

Shark Inference API

from shark_runner import SharkInference

shark_module = SharkInference(
        module = torch.nn.module class.
        (input,)  = inputs to model (must be a torch-tensor)
        dynamic (boolean) = Pass the input shapes as static or dynamic.
        device = `cpu`, `gpu` or `vulkan` is supported.
        tracing_required = (boolean) = Jit trace the module with the given input, useful in the case where jit.script doesn't work. )

result = shark_module.forward(inputs)

Model Tracking (Shark Inference)

Hugging Face Models	Torch-MLIR lowerable	SHARK-CPU	SHARK-CUDA	SHARK-METAL
BERT	✔️ (JIT)	✔️
Albert	✔️ (JIT)	✔️
BigBird	✔️ (AOT)
DistilBERT	✔️ (AOT)
GPT2	❌ (AOT)

TORCHVISION Models	Torch-MLIR lowerable	SHARK-CPU	SHARK-CUDA	SHARK-METAL
AlexNet	✔️ (Script)
DenseNet121	✔️ (Script)
MNasNet1_0	✔️ (Script)
MobileNetV2	✔️ (Script)
MobileNetV3	✔️ (Script)
Unet	❌ (Script)
Resnet18	✔️ (Script)	✔️
Resnet50	✔️ (Script)	✔️
Resnext50_32x4d	✔️ (Script)
ShuffleNet_v2	❌ (Script)
SqueezeNet	✔️ (Script)	✔️
EfficientNet	✔️ (Script)
Regnet	✔️ (Script)
Resnest	❌ (Script)
Vision Transformer	✔️ (Script)
VGG 16	✔️ (Script)
Wide Resnet	✔️ (Script)	✔️
RAFT	❌ (JIT)

For more information refer to MODEL TRACKING SHEET

Shark Trainer API

Models	Torch-MLIR lowerable	SHARK-CPU	SHARK-CUDA	SHARK-METAL
BERT	❌	❌
FullyConnected	✔️	✔️

Related Project Channels

• Upstream IREE issues: Feature requests, bugs, and other work tracking
• Upstream IREE Discord server: Daily development discussions with the core team and collaborators
• iree-discuss email list: Announcements, general and low-priority discussion
• MLIR topic within LLVM Discourse: IREE is enabled by and heavily relies on MLIR. IREE sometimes is referred to in certain MLIR discussions. Useful if you are also interested in MLIR evolution.

License

nod.ai SHARK is licensed under the terms of the Apache 2.0 License with LLVM Exceptions. See LICENSE for more information.