SGLang is a framework for running inference for large language models and multimodal models, meaning it processes inputs to produce model outputs such as text or other media. It is used to serve and accelerate open AI models and related workloads.
Borrowing it
Nothing to install: this file belongs to sgl-project/sglang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sgl-project/sglang/main/.claude/skills/llm-torch-profiler-analysis/SKILL.mdgit clone --depth 1 https://github.com/sgl-project/sglangWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sgl-project/sglang/llm-torch-profiler-analysis)<a href="https://agentmods.dev/skills/sgl-project/sglang/llm-torch-profiler-analysis"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/llm-torch-profiler-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sgl-project/sglang/llm-torch-profiler-analysis"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/llm-torch-profiler-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 128 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Data Exfiltration · line 380 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.06480 |
| Opus 5 | $0.00042 | $0.03240 |
| Sonnet 5 | $0.00017 | $0.01296 |
| Haiku 4.5 | $0.00008 | $0.00648 |
Grade A, and why
llm-torch-profiler-analysis scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://127.0.0.1:8000/start_profile \ How it starts
The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified LLM Torch Profiler Analysis
Overview
Use this skill for torch.profiler analysis across:
sglangvllmTensorRT-LLMTokenSpeed
There is only one public workflow:
triage
Preferred unified entrypoint:
Backwards-compatibility shim (kept so older docker exec ... analyze_sglang_torch_profile.py ... calls keep working; it just forwards to the unified entrypoint):
Markdown bundling helper:
triage always prints the same three tables:
- kernel table
- overlap-opportunity table
- fuse-pattern table
By default, all three tables only render rows at or above 1.0% cumulative GPU-time share.
Rows below that are hidden by default unless the user asks for a lower cutoff.
Keep the fuse-pattern table source-backed and deterministic. Do not turn it into a fuzzy matcher.
If exact source-backed matching is weak but a kernel cluster is still close to a known family, add one short note after the tables with exactly one of:
highmediumlow
Capability Matrix
| Capability | SGLang | vLLM | TensorRT-LLM | TokenSpeed |
|---|---|---|---|---|
| Existing trace triage | yes | yes | yes | yes |
| Single-trace live capture | yes | yes, if torch profiler is enabled on server | requires profiler control endpoints | yes, if /start_profile and /stop_profile are exposed |
| Two-trace mapping+formal triage | yes | yes | yes | yes |
| Stage-separated live workload | yes | yes | yes, with a writable shared trace dir or per-stage host runner | yes, via workload-separated HTTP capture |
--profile-by-stage capture |
yes | no | no | no |
--profile-prefix control |
yes | usually ignored on HTTP profiler route | usually ignored on HTTP profiler route | yes, mapped to profile_id |
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/fuse-overlap-catalog.md 93 KB
- references/heuristics.md 3.8 KB
- references/overlap-catalog.md 24 KB
- references/source-map.md 1.4 KB
- references/vllm-torch-compile-fusions.md 7.5 KB
- scripts/analyze_llm_torch_profile.py 31 KB runs code
- scripts/analyze_sglang_torch_profile.py 506 B runs code
- scripts/make_trtllm_py_executor_override.py 4.3 KB runs code
- scripts/probe_llm_server.py 6.8 KB runs code
- scripts/profile_common.py 39 KB runs code
- scripts/render_triage_markdown_bundle.py 7.6 KB runs code
- scripts/run_llm_single_model_matrix_host.sh 9.4 KB runs code
- scripts/run_sglang_torch_profile_host.sh 7.0 KB runs code
- scripts/run_trtllm_pytorch_profile_host.sh 11 KB runs code
- scripts/run_vllm_torch_profile_host.sh 8.9 KB runs code
- scripts/triage_kernel_helpers.py 92 KB runs code
- scripts/triage_overlap_helpers.py 56 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 563 lines · 84 tokens per session scan A 90c70c1616e9
llm-torch-profiler-analysis is a skill published in the GitHub repository sgl-project/sglang (35,749 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 6,480 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
perf-analyze
Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill), nsys + ncu per-kernel…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).