PyTorch · LLM inference and serving

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware.

Orchestra-Research/AI-Research-SKILLs

QAI ModelBuilder. An agent skill from qualcomm/qai-appbuilder.

qualcomm/qai-appbuilder

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Half-Quadratic Quantization for LLMs without calibration data.

Orchestra-Research/AI-Research-SKILLs

Explains RWKV, a hybrid that trains in parallel like a GPT and runs inference like an RNN with constant memory per token, plus usage, fine-tuning and troubleshooting.

Orchestra-Research/AI-Research-SKILLs

Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch) so it conforms to the pass framework's conventions and auto-registers.

amd/Quark

Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

amd/Quark

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks.

davila7/claude-code-templates

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).

wshobson/agents

Root-cause a vLLM torch-nightly CI regression report. An agent skill from pytorch/test-infra.

pytorch/test-infra

Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.

NVIDIA/skills

Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer.

pytorch/test-infra

Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.

databricks/databricks-agent-skills

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.

NVIDIA/skills

InternVideo2-CLIP L14 (TAO videoclip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment.

NVIDIA/skills

PyTorch-based TAO image classification. An agent skill from NVIDIA/skills.

NVIDIA/skills

Apply existing ShapeShifter graph passes to an .onnx model via the quark-cli shapeshifter CLI or a ShapeShifter YAML.

amd/Quark

Diagnose failed Quark installation, PTQ execution, script generation, or export attempts.

amd/Quark

L3 recipe that runs a Torch LLM PTQ end-to-end for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input): quantize → validate → evaluate.

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Route Quark user goals to the correct atomic skill or workflow.

amd/Quark

Installs or verifies AMD Quark and ensures the selected Python environment has an accelerator-matched PyTorch.

amd/Quark

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request…

amd/Quark

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline).

NVIDIA/skills

优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供…

majiayu000/spellbook

Use this sub-skill for Torch-TensorRT model compilation, dynamic input planning, torch.export workflows, save/load formats, raw TensorRT engines, and compile-time troubleshooting.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging…

VectorSpaceLab/AREX-Skill

A skill your agent uses when planning or auditing TorchVision reference training/evaluation workflows for classification, quantization, detection, segmentation, video classification, optical flow…

VectorSpaceLab/AREX-Skill