minus-one

Human

Pennsylvania State UniversityPA

Pinned Repositories

Bash-Snippets
A collection of small bash scripts for heavy terminal users
Language:Shell00
dotfiles
Config files
Language:Shell00
dynolog
Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.
Language:C++00
hetero-partition-opt
Optimization for Heterogeneous Partitioning
Language:Python10
inference
Reference implementations of inference benchmarks
Language:Python0 1 00
memcpy-bench
A tiny set of microbenchmarks to measure different ways to copy data to a device
Language:C++0 1 00
onnxruntime
ONNX Runtime: cross-platform, high performance scoring engine for ML models
Language:C++00
QuaggaRoutingExample
A simple example on using the quagga router + Lab report
Language:TeX00
reference
Reference implementations of MLPerf benchmarks
Language:Python0 2 00
splitrpc
A {Control + Data} Path Splitting RPC Stack for ML Inference Serving
Language:C++20

minus-one/splitrpc
A {Control + Data} Path Splitting RPC Stack for ML Inference Serving
Language:C++20
minus-one/hetero-partition-opt
Optimization for Heterogeneous Partitioning
Language:Python10
minus-one/Bash-Snippets
A collection of small bash scripts for heavy terminal users
Language:Shell00
minus-one/dotfiles
Config files
Language:Shell00
minus-one/dynolog
Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.
Language:C++00
minus-one/inference
Reference implementations of inference benchmarks
Language:Python0 1 00
minus-one/memcpy-bench
A tiny set of microbenchmarks to measure different ways to copy data to a device
Language:C++0 1 00
minus-one/onnxruntime
ONNX Runtime: cross-platform, high performance scoring engine for ML models
Language:C++00
minus-one/QuaggaRoutingExample
A simple example on using the quagga router + Lab report
Language:TeX00
minus-one/reference
Reference implementations of MLPerf benchmarks
Language:Python0 2 00
minus-one/scholar.py
A parser for Google Scholar, written in Python
Language:Python
minus-one/sir_plus
SIR+ is a heterogeneous concurrent execution engine for DNN inference
2 0
minus-one/SoPaper
Automatically Search and Download Papers
Language:Python