nvidia/tensorrt-llm

1

perf-nsight-compute-analysis Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy di…

nvidia/tensorrt-llm

25

2

kernel-triton-writing ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (…

nvidia/tensorrt-llm

19

3

perf-optimization Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel g…

nvidia/tensorrt-llm

17

4

perf-torch-cuda-graphs Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphe…

nvidia/tensorrt-llm

13

5

perf-torch-sync-free >- Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean…

nvidia/tensorrt-llm

12

6

perf-workload-profiling Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iter…

nvidia/tensorrt-llm

11

7

kernel-tileir-optimization Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune…

nvidia/tensorrt-llm

6