Lightweight TEE-based system for secure ONNX model inference using Intel SGX with automated model partitioning to fit within enclave memory constraints.
-
Updated
Oct 12, 2026 - C
#
model-partitioning
Here are 8 public repositories matching this topic...
Multi-SLO, partition-aware batching and provisioning for cost-efficient DNN inference on serverless platforms (built on HarmonyBatch and Gillis)
deep-learning serverless mxnet inference batching slo cost-optimization alibaba-cloud function-compute onnx model-partitioning
-
Updated
Jul 4, 2026 - Jupyter Notebook
Proof-of-concept secure model-distributed LLM inference: layer partitioning across nodes, recurrent pipeline parallelism, AES-GCM encrypted comms, commitment-based verification & HMAC auth.
security encryption pytorch aes-gcm pipeline-parallelism llm distributed-inference model-partitioning
-
Updated
Jul 16, 2026 - Python
Distributed layer inference for transformer LLMs on edge K3s clusters, with Python/PyTorch and native C++/llama.cpp runtimes, GGUF stage shards, Kubernetes manifests, and an Ops UI for monitoring experiments.
python kubernetes raspberry-pi cpp pytorch edge-computing fastapi edge-ai k3s llama-cpp llm-inference gguf distributed-inference model-partitioning
-
Updated
Aug 19, 2026 - C++
Hunyuan3D-2 fork — image→textured 3D→sliced STL + part segmentation. RTX 50-series (Blackwell/sm_120), CUDA 13.0, Python 3.12, PyTorch 2.11+cu130.
pytorch 3d-printing 3d-generation blackwell model-generation python-3-12 hunyuan3d rtx-50-series model-partitioning cuda-13
-
Updated
Jun 23, 2026 - Python
Experimental testbed for partitioned inference of deep neural networks and large language models across Raspberry Pi edge devices and an edge server, orchestrated by the NNPM web application.
raspberry-pi flask reproducible-research tensorflow pytorch testbed edge-computing network-emulation edge-ai wireless-networks large-language-models distributed-inference dnn-partitioning model-partitioning
-
Updated
Oct 26, 2026 - Python
Web-Based Distributed LLM Inference
-
Updated
May 11, 2026 - Rust
Transfer-aware carbon-efficient scheduling framework for simulating distributed deep neural network inference at the edge.
docker distributed-systems machine-learning deep-learning simulation-framework edge-computing edge-ai green-ai ai-inference carbon-aware-computing energy-efficient-computing model-partitioning
-
Updated
Jun 14, 2026 - Python
Add this topic to your repo
To associate your repository with the model-partitioning topic, visit your repo's landing page and select "manage topics."