Skip to main content

perf-optimize

Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the campaign chases, profile-ranked roadmap.yaml (nsys + ncu per-kernel analysis via the perf-nsight-compute-analysis skill), a fixed budget of rounds applying items one at a time gated on measured gain (curve mode uses a Pareto gate; the evaluator accepts, rejects, or pushes back each attempt and nsys-profiles every accept), one final-verification QA benchmark, expected-vs-measured report with Pareto improvement results. Use when the user wants to optimize / improve / speed up a trtllm-serve deployment (throughput, TTFT, TPOT, ITL, e2e latency) or says "run perf-optimize". For diagnosis WITHOUT applying changes, use the perf-analyze workflow instead.

Informations de source

Dépôt
NVIDIA/TensorRT-LLM
Dernière activité de la source
8 septembre 2026 à 13:18
Langue détectée de SKILL.md
anglais
Étoiles
15 066
Forks
2 929

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Affichage de SKILL.md

SKILL.md
Instructions source · Aperçu en lecture seule
nameperf-optimize
descriptionLaunch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the campaign chases, profile-ranked roadmap.yaml (nsys + ncu per-kernel analysis via the perf-nsight-compute-analysis skill), a fixed budget of rounds applying items one at a time gated on measured gain (curve mode uses a Pareto gate; the evaluator accepts, rejects, or pushes back each attempt and nsys-profiles every accept), one final-verification QA benchmark, expected-vs-measured report with Pareto improvement results. Use when the user wants to optimize / improve / speed up a trtllm-serve deployment (throughput, TTFT, TPOT, ITL, e2e latency) or says "run perf-optimize". For diagnosis WITHOUT applying changes, use the perf-analyze workflow instead.