Comments (1)
✨✨ Here's an AI-assisted sketch of how you might approach this issue saved by @simon-mo using Copilot Workspace v0.17
Topic
Can benchmark_throughput and benchmark_latency write their metrics to a JSON file?
Before
- No, currently,
benchmark_throughput.py
andbenchmark_latency.py
do not support writing their metrics directly to a JSON file. The scripts output their results to the console instead, as seen in their respective codebenchmarks/benchmark_throughput.py
andbenchmarks/benchmark_latency.py
. - The
benchmark_serving.py
script, however, does support saving results to a JSON file, as indicated by its code structure and usage of JSON file writing inbenchmarks/benchmark_serving.py
.
After
- Yes,
benchmark_throughput.py
andbenchmark_latency.py
now support writing their metrics directly to a JSON file. - The scripts include a new command-line argument
--output-json
to specify the output file path for the JSON results. - The JSON output includes key metrics such as average latency, throughput, and detailed per-iteration metrics.
- The
benchmark_serving.py
script's existing JSON file writing functionality remains unchanged.
Plan
benchmarks/benchmark_latency.py
(CHANGE)- Add argument parsing for
--output-json
to specify the output JSON file path - Implement JSON writing logic to output latency metrics to the specified JSON file
- Ensure existing console output remains unchanged
- Add argument parsing for
benchmarks/benchmark_throughput.py
(CHANGE)- Add argument parsing for
--output-json
to specify the output JSON file path - Implement JSON writing logic to output throughput metrics to the specified JSON file
- Ensure existing console output remains unchanged
- Add argument parsing for
.buildkite/run-benchmarks.sh
(CHANGE)- Add --output-json arguments to the two benchmarks (throughput and latency) and ensure they are uploaded as artifacts
- For both benchmarks (thoughput and latency), turn them into multiline bash command
- Do not change the benchmark serving output
from vllm.
Related Issues (20)
- [Bug]: : CPU silently doesn't support multi-step (--num-scheduler-steps)
- [Feature]: Batch inference for `llm.chat()` API HOT 1
- [Bug]: crash on Triton backends when start vllm 0.6.1 HOT 5
- [Usage]: Dose vLLM support embedding api of multimodal llm? HOT 3
- [Usage]: Model Qwen2VLForConditionalGeneration does not support LoRA, but LoRA is enabled. HOT 2
- [Installation]: How to install vLLM on Jetson
- [Usage]: Running LLMEngine (or AsyncLLMEngine) in Arrow Flight RPC do_exchange()
- [Installation]: I want to install with CPU follow the guide on windows (wsl2, ubuntu) but the wsl crash. HOT 2
- [Bug]: L40 GPU deepseek-v2 fp8 cuda graph error; Using `--enforce-eager` can run properly. HOT 3
- [Feature]: new possible lora serving implementation? HOT 4
- [Feature]: NotImplementedError: logprobs is not currently supported by the TPU backend
- [Bug]: vllm-cpu docker gguf: AttributeError: '_OpNamespace' '_C' object has no attribute 'ggml_dequantize' HOT 1
- [Installation]: Container image do not build Dockerfile.cpu HOT 3
- [Usage]: Weird vram usage and increase in use HOT 5
- [Usage]: Is DynamicCache supported in vllm? HOT 4
- [Misc]: Speed of serving Starcoder models
- [Usage]: Best engine arguments for large batch inference HOT 2
- [Bug]: (critical bug) random does not work after import vllm HOT 3
- [Feature]: APC introspection interface HOT 1
- [Performance]: Suitable draft model for llama3.1 8b HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vllm.