Perf Host Analysis
NVIDIA/TensorRT-LLM/.claude/skills/perf-host-analysis
ai-mlResmi
Resmi Sağlayıcı Skill'iView repo
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-a
Dosyalar12 dosya
SKILL.md353 satır
Loading editor…
Kurulum
ÖnerilenTek komut — ajanınız otomatik olarak devreye alır.
Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.
veya
Manuel Kurulum
Daha fazla adımArşivi indirin ve dosyaları projenize manuel olarak ekleyin.
Skill detayları
Versiyonv1.0.0
YazarNVIDIA
Kategoriai-ml
Skill IDNVIDIA/TensorRT-LLM/.claude/skills/perf-host-analysis
Dosyalar12 dosya
İlgili skill'ler
Exec Env CheckCheck the local execution environment for GPU availability, Docker support, and Slurm access. Returns the execution scenario (`satisfied, local, docker`, `satisfied, local, direct`, `satisfied, slurm, local`, or `not_satisfied`), the number of available GPUs, and the GPU type. On Slurm login nodes without local GPUs, the cluster is identified by delegating the hostname to internal-env-info (hostname-based mode), which owns the hostname → cluster_name patterns; GPU type and gpus_per_node then comExec Local CompileCompile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.Exec Local DockerExecute a TensorRT-LLM workload locally in Docker. Runs a fully-resolved Docker command in background, monitors completion, reads logs, and reports results. Workflow-agnostic — does not need to know if the workload is pytest, eval, benchmark, or a custom script.Exec Local SlurmSubmit and monitor a Slurm job on a local cluster. Supports two modes: (1) Persistent allocation (default) — allocates nodes once via nohup salloc, imports the container once, installs once, and reuses across runs by setting SLURM env vars and running the sbatch script via bash. (2) One-shot sbatch — submits a fully-generated Slurm script via sbatch, polls job status, reads logs on completion, and reports results. Workflow-agnostic — handles pytest, eval, benchmark, and custom scripts identicallExec Remote SlurmRemote SLURM cluster development via SSH. Use when running jobs, profiling, or developing on a remote SLURM cluster with pyxis/enroot containers. Covers SSH connection management, srun/sbatch/salloc job patterns, tmux-based allocation persistence, file transfer, and safe remote file access. Works with any SLURM cluster accessible via SSH.Exec Slurm CompileCompile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.