Skip to main content

NVIDIA/TensorRT-Edge-LLM

Latest recorded source activity
SkillsMP catalog refreshed
skills collected
15
GitHub stars
631
GitHub forks
153

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Loading the repository README…

Skills in this repository

classification pending

Showing 15 of 15 collected skills.

occupation
unclassified
description

Localize a TensorRT Edge-LLM accuracy mismatch against the model provider's PyTorch reference after few-layer validation identifies a failing component or layer.

updated
occupation
unclassified
description

Implement TensorRT Edge-LLM support for a new Hugging Face checkpoint or model family. Use for a new `model_type`, architecture, text/vision/audio/action component, checkpoint tensor layout, speculative draft, model-specific custom operation, or runtime…

updated
occupation
unclassified
description

Measure dataset accuracy (MMLU and other NeMo Evaluator benchmarks) of a TensorRT Edge-LLM deployment through its OpenAI-compatible chat endpoint with NeMo Evaluator. Use for "benchmark accuracy", "run MMLU/GSM8K/IFEval on this checkpoint", comparing a…

updated
occupation
unclassified
description

Benchmark TensorRT Edge-LLM serving performance (TTFT, inter-token latency, request latency, output throughput, concurrency scaling) through the OpenAI-compatible server with AIPerf. Use for "benchmark performance", "measure TTFT/ITL/tokens per second",…

updated
occupation
unclassified
description

Convert and run one supported Hugging Face checkpoint with TensorRT Edge-LLM. Use for quantization, checkpoint-to-ONNX export, `llm_build`/`visual_build`/`audio_build`, C++ `llm_inference`, the experimental checkpoint-direct `trtedge build`, engine profile…

updated
occupation
unclassified
description

Write or change a C++ test under unittests/. Covers the BDD comment contract, mutation testing, and the substitute engines that drive LLMInferenceRuntime without a serialized engine. Apply whenever adding, migrating, or repairing a GTest case in this…

updated
occupation
unclassified
description

Add or change a TensorRT Edge-LLM CuTe DSL kernel end to end, from the Python kernel source through the KERNEL_VARIANTS registry in kernelSrcs/build_cutedsl.py, GPU-free AOT artifact generation (native or AArch64 cross build), the metadata-driven…

updated
occupation
unclassified
description

Write, edit, or review TensorRT Edge-LLM documentation using the Google developer documentation style guide. Apply to READMEs, tutorials, how-to guides, conceptual and design documents, API and CLI references, and release notes; not ordinary code changes or…

updated
occupation
unclassified
description

Write, select, run, and verify TensorRT Edge-LLM end-to-end model tests. Use when adding or changing a model case, running one model deployment instead of an entire CI job, interpreting model accuracy or baseline failures, or selecting sufficient tests for…

updated
occupation
unclassified
description

List the supported combinations a change reaches and verify them before the change is submitted. Use before coding a change to quantization or checkpoint parsing, checkpoint loading, the lm_head, KV cache, a speculative decoding method or draft, shared linear…

updated
occupation
unclassified
description

Add or repair a few-layer numeric validation case, which compares the first N decoder layers of a checkpoint against a PyTorch golden. Covers when a change needs one, choosing the checkpoint, setting a cosine gate that is measured rather than tuned, and…

updated
occupation
unclassified
description

Select, install, verify, update, or remove TensorRT Edge-LLM, and install this repository's agent skills into Claude Code or Codex. Inspects revision, CPU architecture, GPU or SoC, JetPack/DriveOS, CUDA, TensorRT, and Python, rejects unsupported combinations…

updated
occupation
unclassified
description

Add or change a TensorRT Edge-LLM operation (TensorRT IPluginV3 plugin, native TensorRT layer composition, or runtime-only operation) so one tensor, dtype, shape, layout, serialization, and weight-layout contract holds across the ONNX export route, the…

updated
occupation
unclassified
description

Launch and verify TensorRT Edge-LLM's experimental OpenAI-compatible server for one Hugging Face checkpoint or local checkpoint. Use for `trtedge serve`, OpenAI API requests, server sizing, streaming, tools, media, batching, speculative decoding, or a server…

updated
occupation
unclassified
description

Migrate an existing TensorRT Edge-LLM deployment, integration, or downstream patch between releases, branches, TensorRT/CUDA/JetPack/DriveOS stacks, or checkpoint-family versions; also backport fixes to a release branch. Use when commands, package extras,…

updated
Showing 15 of 15 collected skills.