From f964493274c3c839b2e27453cb70f179090cd027 Mon Sep 17 00:00:00 2001
From: Simon Mo <simon.mo@hey.com>
Date: Mon, 12 Feb 2024 22:53:07 -0800
Subject: [PATCH] [CI] Ensure documentation build is checked in CI (#2842)

---
 .buildkite/test-pipeline.yaml                  | 7 +++++++
 .buildkite/test-template.j2                    | 4 +++-
 docs/source/conf.py                            | 2 ++
 docs/source/index.rst                          | 1 +
 docs/source/quantization/fp8_e5m2_kv_cache.rst | 1 +
 5 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
index 65ac2f74fb8d..2e417ef94032 100644
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -49,3 +49,10 @@ steps:
   commands:
   - pip install aiohttp
   - bash run-benchmarks.sh
+
+- label: Documentation Build
+  working_dir: "/vllm-workspace/docs"
+  no_gpu: True
+  commands:
+  - pip install -r requirements-docs.txt
+  - SPHINXOPTS=\"-W\" make html
diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2
index 7c709b6097fd..7c1cf2b5a9b3 100644
--- a/.buildkite/test-template.j2
+++ b/.buildkite/test-template.j2
@@ -35,13 +35,15 @@ steps:
               - image: "{{ docker_image }}"
                 command: ["bash"]
                 args:
-                - "-c"
+                - '-c'
                 - "'cd {{ (step.working_dir or default_working_dir) | safe  }} && {{ step.command  or (step.commands | join(' && ')) | safe }}'"
+                {% if not step.no_gpu %}
                 resources:
                   requests:
                     nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
                   limits:
                     nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
+                {% endif %}
                 env:
                   - name: HF_TOKEN
                     valueFrom:
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 44c976468ab0..adbe67b21a0c 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -94,3 +94,5 @@ class MockedClassDocumenter(autodoc.ClassDocumenter):
 
 
 autodoc.ClassDocumenter = MockedClassDocumenter
+
+navigation_with_keys = False
diff --git a/docs/source/index.rst b/docs/source/index.rst
index 9b53a643b8d4..32929257661a 100644
--- a/docs/source/index.rst
+++ b/docs/source/index.rst
@@ -89,6 +89,7 @@ Documentation
    :caption: Quantization
 
    quantization/auto_awq
+   quantization/fp8_e5m2_kv_cache
 
 .. toctree::
    :maxdepth: 2
diff --git a/docs/source/quantization/fp8_e5m2_kv_cache.rst b/docs/source/quantization/fp8_e5m2_kv_cache.rst
index 10437260ad96..f1eeb5955095 100644
--- a/docs/source/quantization/fp8_e5m2_kv_cache.rst
+++ b/docs/source/quantization/fp8_e5m2_kv_cache.rst
@@ -9,6 +9,7 @@ The FP8 data format retains 2~3 mantissa bits and can convert float/fp16/bflaot1
 Here is an example of how to enable this feature:
 
 .. code-block:: python
+
     from vllm import LLM, SamplingParams
     # Sample prompts.
     prompts = [