Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
21 lines
1.0 KiB
Markdown
21 lines
1.0 KiB
Markdown
# Benchmarks
|
|
|
|
This directory used to contain vLLM's benchmark scripts and utilities for performance testing and evaluation.
|
|
|
|
## Contents
|
|
|
|
- **Serving benchmarks**: Scripts for testing online inference performance (latency, throughput)
|
|
- **Throughput benchmarks**: Scripts for testing offline batch inference performance
|
|
- **Specialized benchmarks**: Tools for testing specific features like structured output, prefix caching, long document QA, request prioritization, and multi-modal inference
|
|
- **Dataset utilities**: Framework for loading and sampling from various benchmark datasets (ShareGPT, HuggingFace datasets, synthetic data, etc.)
|
|
|
|
## Usage
|
|
|
|
For detailed usage instructions, examples, and dataset information, see the [Benchmark CLI documentation](https://docs.vllm.ai/en/latest/benchmarking/cli/#benchmark-cli).
|
|
|
|
For full CLI reference see:
|
|
|
|
- <https://docs.vllm.ai/en/latest/cli/bench/latency.html>
|
|
- <https://docs.vllm.ai/en/latest/cli/bench/serve.html>
|
|
- <https://docs.vllm.ai/en/latest/cli/bench/throughput.html>
|