Clangd for CUDA Device Code
Compile CUDA for AMD GPUs with zero code changes—breaks NVIDIA lock-in.

Production-ready CUDA profiling when NSight only works in development.
ML engineers and GPU application developers running CUDA workloads
NVIDIA NSight · Triton Proton · Datadog Continuous Profiler
Compile CUDA for AMD GPUs with zero code changes—breaks NVIDIA lock-in.
Reads PHP VM memory from outside the process with zero code changes.
Finally replaces Nvidia's ancient Excel spreadsheet with something that supports Hopper.
Build vLLM from scratch with PagedAttention kernels when llama.cpp already exists.
Unifies bpftop call counts with perf source-line profiling in one TUI.
Rigorous CGM analysis tool with 15+ clinical metrics; disclaimer prevents clinical misuse.