chore(perf): run guidellm benchmarks #3421
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
meta-cla
bot
added
the
CLA Signed
ehhuang
force-pushed
the
pr3421
branch
3 times, most recently
from
859ac24 to
dc6acf8
Compare
ehhuang
force-pushed
the
pr3421
branch
4 times, most recently
from
9ec5404 to
9bcad5d
Compare
ehhuang
requested review from
ashwinb,
bbrowning,
hardikjshah,
leseb,
mattf,
raghotham,
reluctantfuturist,
slekkala1,
terrytangyuan and
yanxi0830
as code owners
ehhuang
force-pushed
the
pr3421
branch
3 times, most recently
from
2d0c298 to
06739b3
Compare
Closed
ehhuang
force-pushed
the
pr3421
branch
2 times, most recently
from
4ddc5e8 to
5662e9e
Compare
ehhuang
added a commit
that referenced
this pull request
Sep 19, 2025
# What does this PR do? As shown in #3421, we can scale stack to handle more RPS with k8s replicas. This PR enables multi process stack with uvicorn --workers so that we can achieve the same scaling without being in k8s. To achieve that we refactor main to split out the app construction logic. This method needs to be non-async. We created a new `Stack` class to house impls and have a `start()` method to be called in lifespan to start background tasks instead of starting them in the old `construct_stack`. This way we avoid having to manage an event loop manually. ## Test Plan CI > uv run --with llama-stack python -m llama_stack.core.server.server benchmarking/k8s-benchmark/stack_run_config.yaml works. > LLAMA_STACK_CONFIG=benchmarking/k8s-benchmark/stack_run_config.yaml uv run uvicorn llama_stack.core.server.server:create_app --port 8321 --workers 4 works.
slekkala1
reviewed
Sep 19, 2025
| # "matplotlib", | ||
| # ] | ||
| # /// | ||
| """ |
There was a problem hiding this comment.
this is used by uv run python scripts/generated_charts.py
slekkala1
reviewed
Sep 19, 2025
| # "stack 4 2" | ||
| "stack 8 2" | ||
| # "vllm 1 2" | ||
| ) |
There was a problem hiding this comment.
nit: do we need to keep these, are these various configs we use for running the benchmarks?
There was a problem hiding this comment.
updated to correspond to the checked in results/
slekkala1
reviewed
Sep 19, 2025
| ## Benchmark Results | ||
|
|
||
| We use [GuideLLM](https://github.com/neuralmagic/guidellm) against our k8s deployment for comprehensive performance testing. | ||
|
|
There was a problem hiding this comment.
Are we still using the scripts run-all-benchmarks.sh and run-benchmark.sh?
|
Will update this with the new |
ehhuang
force-pushed
the
pr3421
branch
2 times, most recently
from
4a81a4e to
6678849
Compare
# What does this PR do? ## Test Plan # What does this PR do? ## Test Plan # What does this PR do? ## Test Plan
|
lgtm |
slekkala1
approved these changes
Sep 23, 2025
iamemilio
pushed a commit
to iamemilio/llama-stack
that referenced
this pull request
Sep 24, 2025
# What does this PR do? As shown in llamastack#3421, we can scale stack to handle more RPS with k8s replicas. This PR enables multi process stack with uvicorn --workers so that we can achieve the same scaling without being in k8s. To achieve that we refactor main to split out the app construction logic. This method needs to be non-async. We created a new `Stack` class to house impls and have a `start()` method to be called in lifespan to start background tasks instead of starting them in the old `construct_stack`. This way we avoid having to manage an event loop manually. ## Test Plan CI > uv run --with llama-stack python -m llama_stack.core.server.server benchmarking/k8s-benchmark/stack_run_config.yaml works. > LLAMA_STACK_CONFIG=benchmarking/k8s-benchmark/stack_run_config.yaml uv run uvicorn llama_stack.core.server.server:create_app --port 8321 --workers 4 works.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Test Plan
See updated README.md