mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-10 04:34:57 +08:00
[CI] Ensure documentation build is checked in CI (#2842)
This commit is contained in:
parent
a4211a4dc3
commit
f964493274
@ -49,3 +49,10 @@ steps:
|
|||||||
commands:
|
commands:
|
||||||
- pip install aiohttp
|
- pip install aiohttp
|
||||||
- bash run-benchmarks.sh
|
- 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
|
||||||
|
|||||||
@ -35,13 +35,15 @@ steps:
|
|||||||
- image: "{{ docker_image }}"
|
- image: "{{ docker_image }}"
|
||||||
command: ["bash"]
|
command: ["bash"]
|
||||||
args:
|
args:
|
||||||
- "-c"
|
- '-c'
|
||||||
- "'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}'"
|
- "'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}'"
|
||||||
|
{% if not step.no_gpu %}
|
||||||
resources:
|
resources:
|
||||||
requests:
|
requests:
|
||||||
nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
|
nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
|
||||||
limits:
|
limits:
|
||||||
nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
|
nvidia.com/gpu: "{{ step.num_gpus or default_num_gpu }}"
|
||||||
|
{% endif %}
|
||||||
env:
|
env:
|
||||||
- name: HF_TOKEN
|
- name: HF_TOKEN
|
||||||
valueFrom:
|
valueFrom:
|
||||||
|
|||||||
@ -94,3 +94,5 @@ class MockedClassDocumenter(autodoc.ClassDocumenter):
|
|||||||
|
|
||||||
|
|
||||||
autodoc.ClassDocumenter = MockedClassDocumenter
|
autodoc.ClassDocumenter = MockedClassDocumenter
|
||||||
|
|
||||||
|
navigation_with_keys = False
|
||||||
|
|||||||
@ -89,6 +89,7 @@ Documentation
|
|||||||
:caption: Quantization
|
:caption: Quantization
|
||||||
|
|
||||||
quantization/auto_awq
|
quantization/auto_awq
|
||||||
|
quantization/fp8_e5m2_kv_cache
|
||||||
|
|
||||||
.. toctree::
|
.. toctree::
|
||||||
:maxdepth: 2
|
:maxdepth: 2
|
||||||
|
|||||||
@ -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:
|
Here is an example of how to enable this feature:
|
||||||
|
|
||||||
.. code-block:: python
|
.. code-block:: python
|
||||||
|
|
||||||
from vllm import LLM, SamplingParams
|
from vllm import LLM, SamplingParams
|
||||||
# Sample prompts.
|
# Sample prompts.
|
||||||
prompts = [
|
prompts = [
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user