FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Optimizing NVIDIA LLM inference with TensorRT-LLM v1.0.0
Use this resource to optimize and serve an LLM at maximum throughput on NVIDIA GPUs
New
- 418 downloads
- 131 likes
- 132 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install tensorrt-llm-nvidia-inferenceWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent guides you through installing TensorRT-LLM (Docker or pip), loading a model, configuring sampling, then starting the service with trtllm-serve. It also says when to prefer vLLM or llama.cpp. Requirements: CUDA 13.0.0, TensorRT 10.13.2 and Python 3.10 to 3.12.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: installation, basic inference and the trtllm-serve service
- references/optimization.md, multi-gpu.md and serving.md: optimization, multi-GPU and serving
Good fit for
- You deploy to production on A100 or H100 GPUs
- You want maximum throughput with FP8 or INT4 quantization
Not for
Tags
- nvidia
- inference
- tensorrt
- production
About
You say
“Deploy Llama 3 on an H100 with TensorRT-LLM and serve it through trtllm-serve.”
Skill published by Orchestra Research under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to optimize and serve an LLM at maximum throughput on NVIDIA GPUs
- Review and adjust the result
Content preview
Files
- LICENSE1.1 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/multi-gpu.md6.8 KB
- references/optimization.md5.7 KB
- references/serving.md10 KB
- SKILL.md5.1 KB
Origin and licence
Listed unmodified
- Author
- Orchestra Research
- Source
- github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/12-inference-serving/tensorrt-llm
- Licence
- MIT
Notice
« tensorrt-llm » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…