What the posting requires
- Required
- PyTorch
- Quantization
- Benchmark automation
- CUDA
- Pruning
- Performance regression detection
- C++
- Distillation
- Telemetry
- Preferred
- GPU performance
- NVIDIA Nsight Systems
- Reduced-precision models
- Transformer workloads
- Memory bandwidth
- NVIDIA Nsight Compute
These tags are our reading of the posting. They can miss something; the original posting is the reference.