BBuf

Inspect LLM torch profiler traces at forward-pass, layer, and kernel level.

Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework.

Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity.

Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families.

Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape.

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.

Perform SGLang code review in the style of human maintainers by consulting the full non-agent PR review episode corpus from project start…

Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or speculative-decoding model.

Replay-first debug flow for SGLang serving problems.

Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform a fixed fair SGLang benchmark against…

Unified LLM torch-profiler triage skill for `sglang`, `vllm`, `TensorRT-LLM`, and `TokenSpeed`.

Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM…