Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/NVIDIA/TensorRT-LLM
/ benchmark_serving.py
File
benchmark_serving.py
tensorrt_llm/serve/scripts/benchmark_serving.py:None–None ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
1
# Adopted from
2
# https://github.com/vllm-project/vllm/blob/200bbf92e8861e2458a6f90bca73f40cc3b1ad1f/benchmarks/benchmark_serving.py
3
# SPDX-License-Identifier: Apache-2.0
4
r
""
"Benchmark online serving throughput.
Callers
nothing calls this directly
Calls
2
main
Function · 0.70
keys
Method · 0.45
Tested by
no test coverage detected