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/generate-profile/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/generate-profile)<a href="https://agentmods.dev/skills/sgl-project/sglang/generate-profile"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/generate-profile.svg" alt="Measured on agentmods" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00038 | $0.01317 |
| Opus 5 | $0.00019 | $0.00659 |
| Sonnet 5 | $0.00008 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
generate-profile 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 8d 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.
if curl -s http://127.0.0.1:<port>/health 2>/dev/null | grep -q "ok\|healthy"; then How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate an E2E Profile of an SGLang Server Run
This skill launches an SGLang server, validates it with a quick accuracy test, generates a profiling trace, and returns the profile file path.
Prerequisites
- A working SGLang installation (
pip install -e .or equivalent) - At least one available CUDA GPU
Step-by-step Workflow
Step 1: Launch the server
CUDA_VISIBLE_DEVICES=<gpu_id> sglang serve --model-path <model> --port <port> &
- Default model:
Qwen/Qwen3-8B(good balance of speed and quality) - Default port:
30000 - The server runs in the background. Save the PID for cleanup.
- Use the GPU specified by the user's preferences (check memory files for GPU preferences).
Step 2: Wait for server readiness
Poll the health endpoint until the server is ready:
for i in $(seq 1 120); do
if curl -s http://127.0.0.1:<port>/health 2>/dev/null | grep -q "ok\|healthy"; then
echo "Server ready"
break
fi
sleep 5
done
The server prints "The server is fired up and ready to roll!" to stdout when ready. The health endpoint returns 200 once the server can accept requests.
Typical startup time: 30-90 seconds depending on model size and whether CUDA graphs are being compiled.
Step 3: Validate accuracy (sanity check)
python3 -m sglang.test.run_eval --host 127.0.0.1 --port <port> --eval-name gsm8k --num-examples 20
- Expected accuracy: > 0.8 for capable models (Qwen3-8B, Llama-3.1-8B-Instruct, etc.)
- This is a quick sanity check, not a rigorous benchmark.
sglang.test.few_shot_gsm8kis deprecated; use the unifiedrun_evalentrypoint.- If you intentionally need the old completion-style GSM8K path, add
--api completion. - If accuracy is unexpectedly low, something is wrong — do not proceed to profiling.
Step 4: Generate the profile
python3 -m sglang.test.send_one --profile
This command:
- Sends a request to the server
- Triggers the profiler for 5 steps (default)
- Generates a trace file under
/tmp/<timestamp>/ - The trace directory contains:
<timestamp>-TP-0.trace.json.gz— Chrome trace format (open inchrome://tracingor Perfetto)server_args.json— the server configuration used
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.
- 8d ago First seen · 144 lines · 38 tokens per session scan A 0fcd80691c8c
generate-profile is a skill published in the GitHub repository sgl-project/sglang (35,551 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 1,317 once invoked, about $0.0002 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
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
perf-optimize
Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline 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) sizing the headroom the…
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 + torch-profiler…
fireworks-ai-inference
Fast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.
ort
ONNX Runtime in Rust via the ort crate (2.x): loading sessions, configuring CPU/CoreML/CUDA execution providers, tensor I/O with ndarray, async-safe spawnblocking wrapping, global thread-pool init, and debugging provider/opset issues.