
Guides an agent through diagnosing NVSHMEM runtime failures and drafting bug reports
- Open source
- 4K GitHub stars
- Developer tools


Guides an agent through diagnosing NVSHMEM runtime failures and drafting bug reports

Guides an agent through GPU DataFrame work with NVIDIA cuDF and dask-cuDF

Adds autotuning with cached config selection to CuTile GPU kernels

Audits Jetson memory usage and verifies whether freed DRAM is actually reclaimed

Guides an agent through iterative profiling and tuning of cuTile GPU kernels in TileGym

Guides writing and debugging GPU-accelerated RDKit cheminformatics code with nvMolKit

Guides an agent through porting HPC code to GPUs, profiled with Nsight Systems

Collects and packages NVSHMEM put/get perftest results with system and topology evidence

Diagnoses JVM performance problems like high CPU, leaks, deadlocks and GC pauses with JDK

Guides setup, GPU simulation targets, QPU access and @cudaq.kernel authoring in CUDA-Q

Read-only health snapshot of a Jetson device: memory, GPU, thermal, power, services

Guides an agent to write, debug and validate cuTile GPU kernels in Python
The closest alternatives to Compute sanitizer diagnose cuda bugs are Nvshmem troubleshoot and report bugs, Accelerated computing cudf, Tilegym cutile autotuning, Jetson memory audit and Tilegym improve cutile kernel perf.
Yes. Nvshmem troubleshoot and report bugs, Accelerated computing cudf, Tilegym cutile autotuning have a free or open-source option.