Skip to main content
BBuf
GitHub 创作者资料

BBuf

按仓库查看 1 个 GitHub 仓库中的 12 个已收集 skills。

已收集 skills
12
仓库
1
更新
2026年7月28日
仓库分布

Skills 分布在哪些仓库

按已收集 skill 数展示主要仓库,并显示它们在该创作者目录中的占比和职业覆盖。

仓库浏览

仓库与代表性 skills

sglang-model-day0-support
软件开发工程师

Build or audit an evidence-driven SGLang Day-0 support program for a new LLM, VLM, MoE, hybrid-attention, or speculative-decoding model. Use when Codex needs to map a model architecture into SGLang runtime work, design a public support PR DAG, create…

2026年7月28日
model-pr-history-knowledge
软件开发工程师

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed 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…

2026年7月28日
llm-torch-profiler-analysis
软件开发工程师

Unified LLM torch-profiler triage skill for `sglang`, `vllm`, `TensorRT-LLM`, and `TokenSpeed`. Use it to inspect an existing `trace.json(.gz)` or profile directory, or to drive live profiling against a running server when supported and return one three-table…

2026年7月28日
llm-pipeline-analysis
软件开发工程师

Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.

2026年7月28日
llm-serving-auto-benchmark
软件开发工程师

Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, TokenSpeed, or another serving framework. Use when a user wants to find the best deployment command for one model across multiple serving frameworks under the same…

2026年7月28日
llm-serving-capacity-planner
软件开发工程师

Parse SGLang/vLLM startup logs to explain GPU memory use and request capacity. Use for KV cache budget, mem-fraction-static comparisons, OOM triage, and max-concurrency estimates.

2026年7月28日
model-architecture-diagram
软件开发工程师

Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model…

2026年7月28日
model-compute-simulation
软件开发工程师

Build an operator-level compute template for an LLM and estimate FLOPs/MFU for a serving shape. Use when you need tensor shapes, per-op FLOPs, kernel-to-op MFU mapping, or parallelism what-if analysis.

2026年7月28日
已展示 8 / 12 个已收集 Skill。
已展示 1 / 1 个仓库
已展示全部仓库