perf-torch-cuda-graphs
perf-torch-cuda-graphs is a Model training & evaluation skill for AI agents, published by NVIDIA in the TensorRT-LLM repository on GitHub. Skillspace rates perf-torch-cuda-graphs C (74/100) and it passed the safety scan; the rating is based on static analysis only.
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 14,127
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 76 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 3 other repositories, in 0 collections
- Scope
- Vendor-specific: built around one product. About applying CUDA Graphs to public PyTorch and TensorRT frameworks
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.