Skip to main content
在 Manus 中运行任何 Skill
一键导入
$pwd:
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,并展示近似职业覆盖。

已收集 skills
12
仓库
1
职业领域
1
更新
2026-05-26
职业覆盖
该创作者主要覆盖的职业大类。
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

#001
AI-Infra-Auto-Driven-SKILLS
12 个 skills48341更新于 2026-05-26
占该创作者 100%
vllm-sota-humanize-loop
软件开发工程师

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.

2026-05-26
model-pr-history-knowledge
数据科学家

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.

2026-05-26
sglang-sota-humanize-loop
软件开发工程师

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.

2026-05-26
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.

2026-05-26
sglang-humanize-review
软件质量保证分析师与测试员

Perform SGLang code review in the style of human maintainers by consulting the 2024-2025 non-agent PR review corpus, including inline code snippets, original multilingual comments, and discussion threads. Use when reviewing SGLang PRs, diffs, patches, or local changes for correctness, tests, performance, GPU/runtime risks, API compatibility, and maintainability.

2026-05-20
llm-serving-capacity-planner
网络与计算机系统管理员

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.

2026-05-20
model-compute-simulation
数据科学家

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.

2026-05-20
llm-serving-auto-benchmark
软件开发工程师

Framework-independent LLM serving benchmark skill for comparing SGLang, vLLM, TensorRT-LLM, 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 workload, GPU budget, and latency SLA.

2026-05-16
当前展示该仓库 Top 8 / 12 个已收集 skills。
已展示 1 / 1 个仓库
已展示全部仓库