biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Benchmark] Cleanup deprecated nightly benchmark and adjust the docstring for performance benchmark (#25786)

Browse Source 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
This commit is contained in:
Kuntai Du
2025-10-29 21:43:37 -07:00
committed by GitHub
parent b5d70751d8
commit 8bff831f0a
29 changed files with 10 additions and 1289 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/contributing/benchmarks.md
View File

@@ -9,7 +9,6 @@ vLLM provides comprehensive benchmarking tools for performance testing and evalu
- **[Benchmark CLI](#benchmark-cli)**: `vllm bench` CLI tools and specialized benchmark scripts for interactive performance testing
- **[Parameter sweeps](#parameter-sweeps)**: Automate `vllm bench` runs for multiple configurations
- **[Performance benchmarks](#performance-benchmarks)**: Automated CI benchmarks for development
- **[Nightly benchmarks](#nightly-benchmarks)**: Comparative benchmarks against alternatives
[Benchmark CLI]: #benchmark-cli
@@ -1167,7 +1166,7 @@ docker run -it --entrypoint /bin/bash -v /data/huggingface:/root/.cache/huggingf
Then, run below command inside the docker instance.
```bash
bash .buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
bash .buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
```
When run, benchmark script generates results under **benchmark/results** folder, along with the benchmark_results.md and benchmark_results.json.
@@ -1185,7 +1184,7 @@ For more results visualization, check the [visualizing the results](https://gith
The latest performance results are hosted on the public [vLLM Performance Dashboard](https://hud.pytorch.org/benchmark/llms?repoName=vllm-project%2Fvllm).
More information on the performance benchmarks and their parameters can be found in [Benchmark README](https://github.com/intel-ai-tce/vllm/blob/more_cpu_models/.buildkite/nightly-benchmarks/README.md) and [performance benchmark description](../../.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md).
More information on the performance benchmarks and their parameters can be found in [Benchmark README](https://github.com/intel-ai-tce/vllm/blob/more_cpu_models/.buildkite/nightly-benchmarks/README.md) and [performance benchmark description](../../.buildkite/performance-benchmarks/performance-benchmarks-descriptions.md).
### Continuous Benchmarking
@@ -1210,11 +1209,3 @@ The benchmarking currently runs on a predefined set of models configured in the
#### Viewing Results
All continuous benchmarking results are automatically published to the public [vLLM Performance Dashboard](https://hud.pytorch.org/benchmark/llms?repoName=vllm-project%2Fvllm).
## Nightly Benchmarks
These compare vLLM's performance against alternatives (`tgi`, `trt-llm`, and `lmdeploy`) when there are major updates of vLLM (e.g., bumping up to a new version). They are primarily intended for consumers to evaluate when to choose vLLM over other options and are triggered on every commit with both the `perf-benchmarks` and `nightly-benchmarks` labels.
The latest nightly benchmark results are shared in major release blog posts such as [vLLM v0.6.0](https://blog.vllm.ai/2024/09/05/perf-update.html).
More information on the nightly benchmarks and their parameters can be found [here](../../.buildkite/nightly-benchmarks/nightly-descriptions.md).