LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics.
Install Kernel Profiling
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profiling --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/system/profiling .claude/skills/kernel-profiling && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .claude/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profilingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profiling --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/system/profiling .agents/skills/kernel-profiling && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .agents/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profiling --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/system/profiling .cursor/skills/kernel-profiling && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .cursor/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ZJLi2013/awesome-kernel-skills.git --path skills/system/profiling--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profiling --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/system/profiling .gemini/skills/kernel-profiling && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .gemini/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profilingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/system/profiling .github/skills/kernel-profiling && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .github/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZJLi2013/awesome-kernel-skills kernel-profiling --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJLi2013/awesome-kernel-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/system/profiling .opencode/skills/kernel-profiling && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kernel-profiling" agent skill from https://github.com/ZJLi2013/awesome-kernel-skills/tree/main/skills/system/profiling into .opencode/skills/kernel-profiling/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-profiling", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
kernel-profiling- GitHub stars
- 102
- Token cost
- ~696 tokens
- SKILL.md length
- 147 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- None found
At a glance
Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics.
- Works in 5 steps: Detect GPU vendor (scripts/detect_gpu.py) → Run appropriate profiler (NCU or rocprof) → Parse output into structured metrics → …
- Profiling kernels
- SKILL.md covers Overview, NVIDIA: Nsight Compute (NCU), AMD: rocprof and Output Format, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kernel Profiling is an agent skill from ZJLi2013/awesome-kernel-skills. Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics. Produces structured metrics.json with throughput, bandwidth, occupancy, and bottleneck classification. Use when profiling kernels, collecting NCU/rocprof data, or diagnosing performance issues.
Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Performance optimization and OKRs and executive reporting. It works with NVIDIA AI Platform.
When your agent uses it
- Profiling kernels
- Collecting NCU/rocprof data
- Diagnosing performance issues
Example prompts
- “/kernel-profiling”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Detect GPU vendor (scripts/detect_gpu.py)
- Run appropriate profiler (NCU or rocprof)
- Parse output into structured metrics
- Classify bottleneck (memory / compute / latency)
- Feed into bottleneck-diagnosis skill for optimization recommendations
What it can do on your machine
Read from SKILL.md and the folder at commit aba7662. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, python and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Kernel Profiling loads about 696 tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 147 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 147 words (~696 tokens).
“Profiling is the first step in any kernel optimization loop. This skill covers collecting hardware performance counters and deriving actionable metrics on both NVIDIA and AMD GPUs.”
- name
- kernel-profiling
Files
Just SKILL.md in skills/system/profiling of ZJLi2013/awesome-kernel-skills.
Open the folder on GitHubat commit aba7662
Compare with similar skills
Kernel Profiling next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kernel Profiling this skillZJLi2013/awesome-kernel-skills | 102 | — | ~696 | Automated safety check: Pass | None | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| Tilelang SkillslowlyC/agent-gpu-skills | 169 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Ppu Acu Joint Profilealibaba/atrex-kernel-agent | 154 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Nemo Mbridge Perf Moe Optimization WorkflowNVIDIA/skills | 3.5k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 900 | — | ~2.8k | Automated safety check: Pass | None |
Similar skills
Tilelang Skill
slowlyC/agent-gpu-skills
Write, debug, and optimize TileLang kernels from local upstream language, JIT, autotuning, profiling, compiler, test, and example source.
Ppu Acu Joint Profile
alibaba/atrex-kernel-agent
Choose and run ACU-only, adaptive PPU in-kernel timeline, or optional bounded joint analysis for a PPU kernel.
- Official
Nemo Mbridge Perf Moe Optimization Workflow
NVIDIA/skills
Evidence-gated workflow for MoE performance optimization in Megatron Bridge.
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
- Official
Tao Run Deft Pas
NVIDIA/skills
Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data.
More from ZJLi2013/awesome-kernel-skills
All 12 skills in this repoCross Entropy Kernel
ZJLi2013/awesome-kernel-skills
Optimize fused cross-entropy loss kernels in Triton for NVIDIA and AMD GPUs.
Flash Attention Kernel
ZJLi2013/awesome-kernel-skills
Optimize FlashAttention-style fused attention kernels in Triton for NVIDIA and AMD GPUs.
Fused Moe Kernel
ZJLi2013/awesome-kernel-skills
Optimize Fused Mixture-of-Experts (MoE) kernels in Triton for NVIDIA and AMD GPUs.
Gemm Kernel Optimization
ZJLi2013/awesome-kernel-skills
Optimize dense matrix multiplication (GEMM) kernels in Triton for NVIDIA and AMD GPUs.
Iterative Kernel Optimization Loop
ZJLi2013/awesome-kernel-skills
Orchestrates continuous kernel optimization by chaining profiling, bottleneck diagnosis, tier-based optimization, verification, and benchmarking into an iterative loop.
Kernel Benchmark
ZJLi2013/awesome-kernel-skills
Unified kernel benchmarking protocol producing JSON results with latency, TFLOPS, GBps, and comparison against PyTorch baselines.
Related
Works with
Categories
Questions about Kernel Profiling
What does Kernel Profiling do?
Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics. Kernel Profiling is an agent skill from ZJLi2013/awesome-kernel-skills. Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics.
When should I use Kernel Profiling?
Kernel Profiling fits situations like: profiling kernels; collecting NCU/rocprof data; diagnosing performance issues.
How do I install Kernel Profiling in Claude Code?
Run `npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a claude-code`. Or copy the skill folder (skills/system/profiling in ZJLi2013/awesome-kernel-skills) into .claude/skills/kernel-profiling in your project. Claude Code loads it when a task matches its description.
How do I install Kernel Profiling in Codex?
Run `npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a codex`. Or copy the skill folder (skills/system/profiling in ZJLi2013/awesome-kernel-skills) into .agents/skills/kernel-profiling in your project. Codex loads it when a task matches its description.
Can I use Kernel Profiling in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJLi2013/awesome-kernel-skills --skill kernel-profiling -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kernel-profiling, .gemini/skills/kernel-profiling, .github/skills/kernel-profiling and .opencode/skills/kernel-profiling in your project.
What does Kernel Profiling need to run?
SKILL.md names no scripts, command-line tools or credentials: Kernel Profiling is instructions for the agent only. Our summary lists: Python 3.
Does Kernel Profiling access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Kernel Profiling safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Kernel Profiling use?
No licence was found for Kernel Profiling or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Kernel Profiling use?
About 696 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Kernel Profiling?
Skills that share tags, products or a category with Kernel Profiling: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), Tilelang Skill (slowlyC/agent-gpu-skills, 169 stars), Ppu Acu Joint Profile (alibaba/atrex-kernel-agent, 154 stars) and Nemo Mbridge Perf Moe Optimization Workflow (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kernel Profiling?
ZJLi2013 (a GitHub user) maintains it in ZJLi2013/awesome-kernel-skills, which has 102 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on March 31, 2026.
Source: ZJLi2013/awesome-kernel-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.