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/.agents/skills/processor-model-parity/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/processor-model-parity)<a href="https://agentmods.dev/skills/sgl-project/sglang/processor-model-parity"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/processor-model-parity/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/processor-model-parity"><img src="https://agentmods.dev/badge/skills/sgl-project/sglang/processor-model-parity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03949 |
| Opus 5.5 | $0.00034 | $0.01580 |
| Sonnet 5.5 | $0.00017 | $0.00790 |
| Haiku 4.5 | $0.00008 | $0.00395 |
Grade A, and why
processor-model-parity scanned grade A with 0 findings 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 3d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Processor model parity
rust/sglang-processor renders chat requests for SGLang's Rust hosts (the Rust
server, sgl-router, the renderer). A model is supported only when, for the same
request body, the processor produces the same prompt text and the same prompt
token ids as Python's OpenAIServingChat. Python is the reference, Dynamo is
the implementation, and SGLang code exists only where the two differ.
Scope: the request -> prompt -> token ids path, plus the checks that let hosts
serve the model's OpenAI requests through /generate (see "OpenAI layer").
Multimodal preprocessing is not covered here: render_request fails on media
content parts, so hosts send those chats to the engine. The fixture generator
serves every checkpoint text-only, so a media case records that rejection.
Done means
- All text should work: every text chat the engine accepts renders and
tokenizes in the processor (sgl-router's
AllText). Only what SGLang rejects or the processor cannot reproduce goes to the engine; list it in the PR. - Chat and completions go through the engine's
/generate, with the router rendering, tokenizing and parsing (lower_chat,lower_completion); the engine's OpenAI route is only theUnsupportedfallback. That needs the cookbook's--reasoning-parserand--tool-call-parserported. Verify the route against a live engine.
The worked example is DeepSeek-V4-Flash-0731: src/render/models/deepseek_v4.rs
plus tests/fixtures/parity/deepseek-v4-flash-0731.json. Paths below are relative
to rust/sglang-processor/ unless they start with python/.
Where a model's code goes
| Piece | File | Needed when |
|---|---|---|
| Identity -> formatter | src/render/selection.rs (select_chat_formatter) |
always; mirror the order of chat_encoding.resolve_chat_encoding_spec |
| Formatter variant | src/render/mod.rs (ChatFormatter, its render_request arm, plus the render_prompt, stop_strs and resolve_thinking arms) |
always |
| SGLang-specific steps | src/render/models/<model>.rs, re-exported in models/mod.rs |
only where Dynamo diverges from Python |
| Parity cases | tests/fixtures/parity/<model-id>.json |
always |
| README row | the render table in README.md |
always |
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.
- 3d ago Changed · -1 lines 8b7bc5ff227a
- 14d ago Changed · +37 lines b4146219263f
- 18d ago Changed · +1 lines 7756d6f98e15
- 19d ago Changed · +19 lines c3c5a0fea32b
- 20d ago First seen · 193 lines · 84 tokens per session scan A 39151872c99c
processor-model-parity is a skill published in the GitHub repository sgl-project/sglang (38,324 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 3,949 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
presentations
Build PowerPoint (PPTX) decks — pptxgenjs when Node is present, python-pptx when not; edit existing decks in place via OOXML — with visual QA before delivery.
jamjet-durability-patterns
Production durability patterns for AI agents on the JVM — crash recovery, audit trails, human-in-the-loop, and replay testing using JamJet runtime.
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.
cargo-test
Skill "cargo-test" from rootwarp/claude-code-plugins-monorepo, covering /cargo-test and instructions.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
kotlin-testing
Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.