Skip to content

[LLM] fix docs for sglang and vllm #963

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
podkidyshev merged 2 commits into from
Jul 7, 2026
Merged

[LLM] fix docs for sglang and vllm #963

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cb99e1b
fix docs for sglang and vllm
podkidyshev Jul 6, 2026
579543e
make wording consistent with the rest of the docs
podkidyshev Jul 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 18 additions & 7 deletions doc/workloads/sglang.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,8 @@ SGLang is a high-throughput and memory-efficient inference engine for LLMs. This
Usage Examples
--------------

Test + Scenario example
~~~~~~~~~~~~~~~~~~~~~~~
Test and Scenario Examples
~~~~~~~~~~~~~~~~~~~~~~~~~~

.. code-block:: toml
:caption: test.toml (test definition)
Expand Down Expand Up @@ -65,11 +65,9 @@ Test-in-Scenario example
docker_image_url = "lmsysorg/sglang:dev-cu13"
model = "Qwen/Qwen3-8B"

[Tests.bench_cmd_args]
random_input = 16
random_output = 128
max_concurrency = 16
num_prompts = 30
Workload-specific test definition sections, such as ``bench_cmd_args`` and ``semantic_eval_cmd_args``, are not
supported under ``[[Tests]]`` in a test scenario. Define them in a test definition TOML and reference that test with
``test_name`` when custom benchmark or semantic-evaluation arguments are needed.


Semantic Validation
Expand All @@ -96,6 +94,19 @@ The ``cli`` string supports ``{model}``, ``{host}``, ``{port}``, ``{url}``, ``{o
placeholders.


Reporting
---------
After a run completes, CloudAI parses ``sglang-bench.jsonl`` and prints serving latency, successful prompt count,
completion rate, throughput, TPS per user, and TPS per GPU. If ``semantic_eval_cmd_args`` is configured, CloudAI also
reports semantic validation accuracy.

The reported metric (``default``) is throughput. Additional supported metrics are ``throughput``, ``tps-per-user``,
``tps-per-gpu``, and ``accuracy``.

CloudAI also provides the scenario-level ``sglang_comparison`` report. It compares SGLang test runs in the scenario and
uses ``bench_cmd_args`` values as comparison labels.


Readiness health checks
-----------------------
Healthcheck fields:
Expand Down
21 changes: 16 additions & 5 deletions doc/workloads/vllm.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,11 +65,9 @@ Test-in-Scenario example
docker_image_url = "nvcr.io#nvidia/ai-dynamo/vllm-runtime:0.7.0"
model = "Qwen/Qwen3-0.6B"

[Tests.bench_cmd_args]
random_input_len = 16
random_output_len = 128
max_concurrency = 16
num_prompts = 30
Workload-specific test definition sections, such as ``bench_cmd_args`` and ``semantic_eval_cmd_args``, are not
supported under ``[[Tests]]`` in a test scenario. Define them in a test definition TOML and reference that test with
``test_name`` when custom benchmark or semantic-evaluation arguments are needed.


Semantic Validation
Expand All @@ -91,6 +89,19 @@ The ``cli`` string supports ``{model}``, ``{host}``, ``{port}``, ``{url}``, ``{o
placeholders.


Reporting
---------
After a run completes, CloudAI parses ``vllm-bench.json`` and prints serving latency, successful prompt count,
completion rate, throughput, TPS per user, and TPS per GPU. If ``semantic_eval_cmd_args`` is configured, CloudAI also
reports semantic validation accuracy.

The reported metric (``default``) is throughput. Additional supported metrics are ``throughput``, ``tps-per-user``,
``tps-per-gpu``, and ``accuracy``.

CloudAI also provides the scenario-level ``vllm_comparison`` report. It compares vLLM test runs in the scenario and
uses ``bench_cmd_args`` values as comparison labels.


Controlling the Number of GPUs
-------------------------------
GPU selection priority, from lowest to highest:
Expand Down
Loading