NVIDIA/TensorRT-Model-Connect is a collection of C++ reference implementations for deploying supported Hugging Face models with NVIDIA TensorRT, a system that runs trained models to produce inference results. It is for developers who want to build and run supported models or evaluate model integrations through TensorRT. The catalogue entries provide skills and instructions for using this model deployment workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/TensorRT-Model-Connect --skill debug-trt-mismatchgit clone --depth 1 https://github.com/NVIDIA/TensorRT-Model-ConnectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/tensorrt-model-connect/debug-trt-mismatch)<a href="https://agentmods.dev/skills/nvidia/tensorrt-model-connect/debug-trt-mismatch"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/debug-trt-mismatch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/tensorrt-model-connect/debug-trt-mismatch"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/debug-trt-mismatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00417 |
| Opus 5.5 | $0.00012 | $0.00167 |
| Sonnet 5.5 | $0.00006 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
debug-trt-mismatch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Debug a TensorRT Mismatch
Find the first family-owned boundary that diverges without changing the workload or acceptance rule.
Start from the owning case
Record the repository revision, checkpoint revision, family testcase, build inputs, runtime root, hardware, seed, and request. Read these files before changing code:
families/<family>/tests/manifests/<case>.jsonfamilies/<family>/tests/thresholds/<case>.jsonfamilies/<family>/tests/test_e2e.py
Reproduce the exact direct E2E path:
PYTHONPATH=core/builder:apps/benchmark:. python3 -m pytest \
families/<family>/tests/test_e2e.py \
--e2e-testcase <case> -vv
Provide the testcase's required TRTMC_BINARY, TRTMC_RUNTIME_ROOT, local
checkpoint, and GPU environment. Do not replace its reference, seed, or
threshold with a smaller smoke test.
Localize inside the family
Separate build, native execution, reference execution, and comparison. Then narrow the first failing boundary in the owning family: inputs and preprocessing, weight mapping, graph output, runtime bindings or state, postprocessing, or the family contract.
Reuse an existing family-local probe or test when one exists. Add a focused family-local diagnostic only when the current evidence cannot identify the boundary. Do not move model policy into core or import another family to share debug code.
Never weaken a correctness gate to make the mismatch disappear. If the gate is suspected to be wrong, demonstrate that independently and request review.
Report the exact reproducer, first divergent boundary, evidence that ruled out earlier stages, smallest owner-local fix, and checks still not run.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -152 lines · -30 tokens per session 4e05cafecdb9
- 1mo ago First seen · 204 lines · 61 tokens per session scan A 2a27694da85e
debug-trt-mismatch is a skill published in the GitHub repository NVIDIA/TensorRT-Model-Connect (280 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 417 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
huggingface-transformers
Use when running or fine-tuning Hugging Face Transformers models in Python — pipeline() inference for text classification and generation, loading weights with AutoModel/AutoTokenizer, devicemap and dtype memory management, tokenizer usage, Trainer fine-tuning, and BGE embeddings for Chinese RAG. Covers transformers…
graphsignal-profiler
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
rocketride-debugging-pipelines
Use when a RocketRide pipeline run failed, errored, or produced wrong/empty output, and you need to find the failing node and fix it. Reads run status and execution traces, diagnoses the cause, and routes back to design or configuration. Also use directly when asked to debug a run.
cutedsl_megamoe
The explicit GenPhase prototype is independently owned by ../nextcutedslmegamoe. This legacy package lazily re-exports its six public GenPhase names. Follow that package's update workflow for GenPhase changes; keep this older snapshot separate. The default backend heuristics do not select GenPhase automatically.
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
weights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform.