LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
Capture torch.profiler traces on a running FlashRec server. An agent skill from sohu-mptc/FlashRec.
Install Profile Serving
$ npx skills add sohu-mptc/FlashRec --skill profile-serving -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sohu-mptc/FlashRec profile-serving --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/sohu-mptc/FlashRec.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/profile-serving .claude/skills/profile-serving && 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 "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .claude/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-servingType 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 sohu-mptc/FlashRec --skill profile-serving -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sohu-mptc/FlashRec profile-serving --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sohu-mptc/FlashRec.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/profile-serving .agents/skills/profile-serving && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .agents/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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 sohu-mptc/FlashRec --skill profile-serving -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sohu-mptc/FlashRec profile-serving --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sohu-mptc/FlashRec.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/profile-serving .cursor/skills/profile-serving && 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 "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .cursor/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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/sohu-mptc/FlashRec.git --path .claude/skills/profile-serving--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 sohu-mptc/FlashRec --skill profile-serving -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sohu-mptc/FlashRec profile-serving --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sohu-mptc/FlashRec.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/profile-serving .gemini/skills/profile-serving && 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 "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .gemini/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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 sohu-mptc/FlashRec profile-servingInstalls 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 sohu-mptc/FlashRec --skill profile-serving -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sohu-mptc/FlashRec.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/profile-serving .github/skills/profile-serving && 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 "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .github/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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 sohu-mptc/FlashRec --skill profile-serving -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sohu-mptc/FlashRec profile-serving --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sohu-mptc/FlashRec.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/profile-serving .opencode/skills/profile-serving && 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 "profile-serving" agent skill from https://github.com/sohu-mptc/FlashRec/tree/main/.claude/skills/profile-serving into .opencode/skills/profile-serving/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "profile-serving", 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
profile-serving- GitHub stars
- 107
- Token cost
- ~312 tokens
- SKILL.md length
- 64 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Capture torch.profiler traces on a running FlashRec server. An agent skill from sohu-mptc/FlashRec.
- The user asks to profile
- SKILL.md covers 采集 and 解读
- Calls curl
- Sglang.benchserving --profile
What it does
Profile Serving is an agent skill from sohu-mptc/FlashRec. Capture torch.profiler traces on a running FlashRec server. Use when the user asks to profile, trace, Chrome trace, startprofile, stopprofile, sglang.benchserving --profile, or 性能剖析.
Its SKILL.md is about 310 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. It works with SGLang. The repository describes itself as: FlashRec is a CUDA-graph engine for generative recommendation: wide beam search (3–5 SID steps, n=50–512+) over a trie-constrained catalog, in-process FP8 serving, and ranked… The licence is Apache-2.0.
When your agent uses it
- The user asks to profile
- Sglang.benchserving --profile
Example prompts
- “/profile-serving”
What it can do on your machine
Read from SKILL.md and the folder at commit 1089682. 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
Shell commands in SKILL.md call:
curl
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
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
Profile Serving loads about 312 tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 64 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
The full file from sohu-mptc/FlashRec at commit 1089682, republished under its Apache-2.0 licence (© sohu-mptc). 64 words, ~312 tokens.
Download SKILL.mdSave it as
.claude/skills/profile-serving/SKILL.md (or your agent's skills folder).- name
- profile-serving
- description
- Capture torch.profiler traces on a running FlashRec server. Use when the user asks to profile, trace, Chrome trace, start_profile, stop_profile, sglang.bench_serving --profile, or 性能剖析.
服务端 Profiling
接口与 SGLang 对齐，可直接给 sglang.bench_serving --profile 用。start/stop
在 GPU worker 线程上生效——不要在 HTTP 线程上包 torch.profiler。
采集
默认输出目录：FLASHREC_TORCH_PROFILER_DIR → SGLANG_TORCH_PROFILER_DIR → /tmp。
scripts/serve.sh 会设成仓库下 profiles/。
curl -s -X POST http://127.0.0.1:8000/start_profile \
-H 'Content-Type: application/json' \
-d '{"output_dir":"./profiles","num_steps":20,"activities":["CPU","GPU"],"with_stack":true}'
curl -s -X POST http://127.0.0.1:8000/stop_profile到 num_steps 会自动停。Body：output_dir、num_steps、start_step、
activities（CPU/GPU）、profile_by_stage、with_stack、record_shapes、
profile_prefix。
Chrome trace 区间名：flashrec.batch.wait / prefill / decode_fwd /
expand / finalize。
解读
- 窄 beam + 低并发：
batch.wait或单请求开销主导，不要据此调 graph - 宽 beam：看
expand是否在 CUDA graph 内；eager expand 说明bs % n != 0或捕获宽度不够 finalize过重：检查FLASHREC_DENSE_FINALIZE（默认1）- 对照 SGLang 时两侧都要用 FlashInfer，并关掉 SGLang overlap schedule
© sohu-mptc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/profile-serving of sohu-mptc/FlashRec.
Open the folder on GitHubat commit 1089682
Compare with similar skills
Profile Serving 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 |
|---|---|---|---|---|---|---|
| Profile Serving this skillsohu-mptc/FlashRec | 107 | — | ~312 | Automated safety check: Pass | Apache-2.0 | |
| LLM Torch Profiler Analysissgl-project/sglang | 37k | 2 repos | ~6.4k | Automated safety check: Pass | Apache-2.0 | |
| SGLang Maintainer-Style ReviewBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~4.6k | Automated safety check: Pass | None | |
| LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~2.8k | Automated safety check: Pass | None | |
| Sglang Diffusion Benchmark Profilesgl-project/sglang | 37k | 2 repos | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| LLM Pipeline Profiler AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~3.9k | Automated safety check: Pass | None |
Similar skills
SGLang Maintainer-Style Review
BBuf/AI-Infra-Auto-Driven-SKILLS
Reviews SGLang changes the way its maintainers do, drawing on a bundled corpus of public PR review threads and a flowchart of how the diff runs.
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.
Sglang Diffusion Benchmark Profile
sgl-project/sglang
A skill your agent uses when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
LLM Pipeline Profiler Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.
Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
More from sohu-mptc/FlashRec
Model Deploy
sohu-mptc/FlashRec
Deploy and serve GenRec checkpoints with FlashRec (install, serve.sh, SID trie, wide-beam knobs, health/curl, FP8, profiling).
Recif Eval
sohu-mptc/FlashRec
Run RecIF beam×concurrency eval and FlashRec vs SGLang/vLLM/TRT-LLM baselines.
Sid Catalog
sohu-mptc/FlashRec
Build SID trie catalogs for FlashRec from OpenOneRec RecIF packed mappings.
Add Model
sohu-mptc/FlashRec
给 FlashRec 引擎接入一个新模型架构（新的 HF checkpoint / 非 Qwen3 结构）。涵盖模型定义、权重合并加载、FP8 双路径、融合 kernel 接线、CUDA graph 兼容、精度校验、以及压测+trace 验证闭环。当用户要"增加/支持/接入新模型"时使用。
Related
Works with
Categories
Questions about Profile Serving
What does Profile Serving do?
Capture torch.profiler traces on a running FlashRec server. An agent skill from sohu-mptc/FlashRec. Profile Serving is an agent skill from sohu-mptc/FlashRec.profiler traces on a running FlashRec server.
When should I use Profile Serving?
Profile Serving fits situations like: the user asks to profile; sglang.benchserving --profile.
How do I install Profile Serving in Claude Code?
Run `npx skills add sohu-mptc/FlashRec --skill profile-serving -a claude-code`. Or copy the skill folder (.claude/skills/profile-serving in sohu-mptc/FlashRec) into .claude/skills/profile-serving in your project. Claude Code loads it when a task matches its description.
How do I install Profile Serving in Codex?
Run `npx skills add sohu-mptc/FlashRec --skill profile-serving -a codex`. Or copy the skill folder (.claude/skills/profile-serving in sohu-mptc/FlashRec) into .agents/skills/profile-serving in your project. Codex loads it when a task matches its description.
Can I use Profile Serving 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 sohu-mptc/FlashRec --skill profile-serving -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/profile-serving, .gemini/skills/profile-serving, .github/skills/profile-serving and .opencode/skills/profile-serving in your project.
What does Profile Serving need to run?
Going by SKILL.md and its folder, Profile Serving needs the command-line tools its instructions call (curl).
Does Profile Serving access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Profile Serving 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 Profile Serving use?
Profile Serving is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Profile Serving use?
About 312 tokens (SKILL.md is roughly 1.2k 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 Profile Serving?
Skills that share tags, products or a category with Profile Serving: LLM Torch Profiler Analysis (sgl-project/sglang, 37k stars), SGLang Maintainer-Style Review (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars), LLM Torch Profiler Trace Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars) and Sglang Diffusion Benchmark Profile (sgl-project/sglang, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Profile Serving?
sohu-mptc (a GitHub organization) maintains it in sohu-mptc/FlashRec, which has 107 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 1, 2026.
Source: sohu-mptc/FlashRec on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.