vllm-project / vllm-project/aibrix
Compare trtllm-bench and vllm-bench differences
Open
area/benchmark
priority/important-soon
- Dominant language
- Go
- Stars
- 5.1k
- Forks
- 694
- Avg merge
- 1d 20h
- Merged PRs (30d)
- 98
Description
### 🚀 Feature Description and Motivation
https://nvidia.github.io/TensorRT-LLM/performance/performance-tuning-guide/benchmarking-default-performance.html
trtllm repo uses `trtllm-bench` in the benchmark, let's compare with vllm-bench tools to check any differences.
### Use Case
to get aligned on the performance numbers and tools
### Proposed Solution
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.