**Agent-ready skills for LLM serving benchmarks, profiler triage, capacity planning, model Day-0 support, code review, incident triage, and model PR history across SGLang, vLLM, TensorRT-LLM, and TokenSpeed — plus SGLang PR and article explainer videos.**
@bbufInspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel…
@bbufFramework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving…
@bbufParse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static…
@bbufAnalyze existing Torch Profiler Chrome traces or capture from SGLang, vLLM, TensorRT-LLM and TokenSpeed servers. Return kernel…
@bbufReturn public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook…
@bbufBuild an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes,…
@bbuf© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
