ophilar's starred repositories
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
nvidia-smi-python
Python code to get GPU stats
Smart-Scientific-Reader
Hammer PDF - Smart Science Reader
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
chilipie-kiosk
Easy-to-use Raspberry Pi image for booting directly into full-screen Chrome, with built-in convenience features for unattended operation. Perfect for dashboards and build monitors.
attention_with_linear_biases
Code for the ALiBi method for transformer language models (ICLR 2022)
FidelityFX-FSR2
FidelityFX Super Resolution 2
local_linear_deshadow
Physics Based Image Deshadowing Using Local Linear Model
flash-attention
Fast and memory-efficient exact attention
Monocular-Depth-Estimation-Toolbox
Monocular Depth Estimation Toolbox based on MMSegmentation.
coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
EfficientFormer
EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
intel-extension-for-pytorch
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Helicopter-Simulation
A complete 6DOF helicopter simulation (physics engine + visualization)