# vLLM: Guardrails and Fix Patterns
🧭 Quick Return to Map
> You are in a sub-page of **LocalDeploy_Inference**.
> To reorient, go back here:
>
> - [**LocalDeploy_Inference** — on-prem deployment and model inference](./README.md)
> - [**WFGY Global Fix Map** — main Emergency Room, 300+ structured fixes](../README.md)
> - [**WFGY Problem Map 1.0** — 16 reproducible failure modes](../../README.md)
>
> Think of this page as a desk within a ward.
> If you need the full triage and all prescriptions, return to the Emergency Room lobby.
Field guide for stabilizing **vLLM-based local inference pipelines**.
Use these checks when models serve correctly on API providers but fail under **high-throughput GPU serving** with vLLM.
---
## Open these first
* Visual recovery: [RAG Architecture & Recovery](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md)
* Retrieval tuning knobs: [Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
* Snippet traceability: [retrieval-traceability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md)
* Ordering & race fixes: [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md), [deployment-deadlock.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/deployment-deadlock.md), [predeploy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md)
* Embedding issues: [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
---
## Core acceptance
* ΔS(question, retrieved) ≤ 0.45
* Coverage ≥ 0.70 for target section
* λ remains convergent across 3 paraphrases and 2 seeds
* Throughput scaling does not shift retrieved citations
---
## Typical vLLM breakpoints and fix
| Symptom | Likely cause | Fix |
| ------------------------------------ | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Works at batch=1 but fails at scale | Context window fragmentation / GPU memory swap | [context-drift.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md), [entropy-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/entropy-collapse.md) |
| Citations disappear at high load | Async batch merge drops offsets | [retrieval-traceability.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md), [data-contracts.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md) |
| Different answers run-to-run | λ flips with batch ordering | [logic-collapse.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md), [rerankers.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md) |
| Index correct but retrieval unstable | Embedding vs metric mismatch in store | [embedding-vs-semantic.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md), [vectorstore-fragmentation.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/vectorstore-fragmentation.md) |
| GPU OOM / crash at warm-up | Preload sequence too large, missing fence | [bootstrap-ordering.md](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md) |
---
## Fix in 60 seconds
1. **Measure ΔS** at batch=1 and batch=32.
If ΔS rises >0.60 only at scale → async batching issue.
2. **Probe λ** across 3 paraphrases. If flips, apply BBAM.
3. **Enforce contracts**: citations must include `snippet_id`, `offsets`.
4. **GPU warm-up**: preload with a dummy batch before first live call.
5. **Verify throughput stability** with replay test (2 seeds, same dataset).
---
## Copy-paste test prompt
```txt
I am running vLLM locally.
Models served with async batching.
Question: "{user_question}"
Please return:
1. ΔS at batch=1 and batch=32
2. λ across 3 paraphrases
3. Whether citations preserved (snippet_id, offsets)
4. Minimal structural fix if ΔS ≥ 0.60
```
---
### 🔗 Quick-Start Downloads (60 sec)
| Tool | Link | 3-Step Setup |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- |
| **WFGY 1.0 PDF** | [Engine Paper](https://github.com/onestardao/WFGY/blob/main/I_am_not_lizardman/WFGY_All_Principles_Return_to_One_v1.0_PSBigBig_Public.pdf) | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + \” |
| **TXT OS (plain-text OS)** | [TXTOS.txt](https://github.com/onestardao/WFGY/blob/main/OS/TXTOS.txt) | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |
---
### Explore More
| Module | Description | Link |
| --- | --- | --- |
| WFGY Core | Canonical framework entry point | [View](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
| Problem Map | Diagnostic map and navigation hub | [View](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
| Tension Universe Experiments | MVP experiment field | [View](https://github.com/onestardao/WFGY/tree/main/TensionUniverse/Experiments) |
| Recognition | Where WFGY is referenced or adopted | [View](https://github.com/onestardao/WFGY/blob/main/recognition/README.md) |
| AI Guide | Anti-hallucination reading protocol for tools | [View](https://github.com/onestardao/WFGY/blob/main/AI_GUIDE.md) |
> If this repository helps, starring it improves discovery for other builders.
> [](https://github.com/onestardao/WFGY)