Skip to main content
skillsmp

Menu

Run any Skill in Manus
with one click
GitHub repository

TensorRT-LLM

TensorRT-LLM contains 2 collected skills from triton-inference-server, with repository-level occupation coverage and site-owned skill detail pages.

triton-inference-server profileView on GitHub
skills collected
2
Stars
5
updated
2026-07-19
Forks
0
Occupation coverage
Network & Computer Systems AdministratorsSoftware Developers
2 occupation categories · 100% classified
repository explorer

Skills in this repository

exec-local-compile
software-developers

Compile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.

2026-07-19
exec-slurm-compile
network-and-computer-systems-administrators

Compile 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.

2026-07-19