From 4f186e2d8f004fe329a98c34a15b54cf84d116e1 Mon Sep 17 00:00:00 2001 From: simon-mo Date: Mon, 12 Feb 2024 16:50:16 -0800 Subject: [PATCH 1/5] ensure documentation build is checked in CI --- .buildkite/test-pipeline.yaml | 7 +++++++ docs/source/conf.py | 2 ++ docs/source/index.rst | 1 + docs/source/quantization/fp8_e5m2_kv_cache.rst | 1 + 4 files changed, 11 insertions(+) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 65ac2f74fb8dc..15e55519e52a8 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" + num_gpus: 0 + commands: + - pip install -r requirements-docs.txt + - SPHINXOPTS="-W" make html \ No newline at end of file diff --git a/docs/source/conf.py b/docs/source/conf.py index 44c976468ab06..adbe67b21a0c8 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -94,3 +94,5 @@ def add_line(self, line: str, source: str, *lineno: int) -> None: autodoc.ClassDocumenter = MockedClassDocumenter + +navigation_with_keys = False diff --git a/docs/source/index.rst b/docs/source/index.rst index 9b53a643b8d46..32929257661ad 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 10437260ad964..f1eeb59550952 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 = [ From 3e83acb47f6313cf409c6b8a71fe10d946afce04 Mon Sep 17 00:00:00 2001 From: simon-mo Date: Mon, 12 Feb 2024 16:54:30 -0800 Subject: [PATCH 2/5] fix template --- .buildkite/test-pipeline.yaml | 4 ++-- .buildkite/test-template.j2 | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 15e55519e52a8..b7d9c2b824f02 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -52,7 +52,7 @@ steps: - label: Documentation Build working_dir: "/vllm-workspace/docs" - num_gpus: 0 + no_gpu: True commands: - pip install -r requirements-docs.txt - - SPHINXOPTS="-W" make html \ No newline at end of file + - SPHINXOPTS="-W" make html diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2 index 7c709b6097fd4..e9d735e857f47 100644 --- a/.buildkite/test-template.j2 +++ b/.buildkite/test-template.j2 @@ -37,11 +37,13 @@ steps: args: - "-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: From 68c10765f93932049177e9411c25031b94499a88 Mon Sep 17 00:00:00 2001 From: simon-mo Date: Mon, 12 Feb 2024 16:58:26 -0800 Subject: [PATCH 3/5] fix template --- .buildkite/test-template.j2 | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2 index e9d735e857f47..1835e7f241ff3 100644 --- a/.buildkite/test-template.j2 +++ b/.buildkite/test-template.j2 @@ -35,8 +35,8 @@ steps: - image: "{{ docker_image }}" command: ["bash"] args: - - "-c" - - "'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}'" + - '-c' + - 'cd {{ (step.working_dir or default_working_dir) | safe }} && {{ step.command or (step.commands | join(' && ')) | safe }}' {% if not step.no_gpu %} resources: requests: From c306fe5182016d351159d710d8c74a61495374ee Mon Sep 17 00:00:00 2001 From: simon-mo Date: Mon, 12 Feb 2024 17:01:41 -0800 Subject: [PATCH 4/5] fix template --- .buildkite/test-template.j2 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2 index 1835e7f241ff3..53528490c8799 100644 --- a/.buildkite/test-template.j2 +++ b/.buildkite/test-template.j2 @@ -36,7 +36,7 @@ steps: command: ["bash"] args: - '-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: requests: From f56732c4f8d80ebcaee3f491c879becfd9847eb7 Mon Sep 17 00:00:00 2001 From: simon-mo Date: Mon, 12 Feb 2024 17:11:19 -0800 Subject: [PATCH 5/5] fix template --- .buildkite/test-pipeline.yaml | 2 +- .buildkite/test-template.j2 | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index b7d9c2b824f02..2e417ef940322 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -55,4 +55,4 @@ steps: no_gpu: True commands: - pip install -r requirements-docs.txt - - SPHINXOPTS="-W" make html + - SPHINXOPTS=\"-W\" make html diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2 index 53528490c8799..7c1cf2b5a9b39 100644 --- a/.buildkite/test-template.j2 +++ b/.buildkite/test-template.j2 @@ -36,7 +36,7 @@ steps: command: ["bash"] args: - '-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: requests: