Loading...
Loading...
Found 24 Skills
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
LLM and ML model deployment for inference. Use when serving models in production, building AI APIs, or optimizing inference. Covers vLLM (LLM serving), TensorRT-LLM (GPU optimization), Ollama (local), BentoML (ML deployment), Triton (multi-model), LangChain (orchestration), LlamaIndex (RAG), and streaming patterns.
Use when an SGLang, vLLM, or TensorRT-LLM serving/model optimization task needs prior model-family PR evidence. Query and read the PR-driven history docs under model-pr-optimization-history before choosing source paths, fast paths, kernel/fusion ideas, regression risks, or validation lanes.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint, switch nemoclaw inference model, change inference runtime, nemoclaw additional model, nemoclaw sub-agent model, openclaw sub-agent, agents.list, sessions_spawn, vlm-demo, nemoclaw tool calling, ollama tool calls, vllm tool-call-parser, raw json in tui, nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference and the root cause is unknown.
Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.
Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR). Use when the user wants to verify config application, debug config issues, or check if AutoDeploy transforms (piecewise CUDA graph, multi-stream, sharding, fusion, etc.) were applied or fell back. Triggers on: "check config", "verify config", "ad-conf-check", "were my configs applied", "config not working", "check if piecewise is enabled", "check log for config", or any request to compare AD YAML settings against runtime behavior.