Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[MISC] Replace input token throughput with total token throughput #8164

Merged
merged 3 commits into from
Sep 4, 2024
Merged

[MISC] Replace input token throughput with total token throughput #8164

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
80a9cc1
Add token throughput
comaniac Sep 4, 2024
1a54fe9
comment
comaniac Sep 4, 2024
6e986c4
Update benchmarks/benchmark_serving.py
comaniac Sep 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 5 additions & 10 deletions benchmarks/benchmark_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,8 +56,7 @@ class BenchmarkMetrics:
total_input: int
total_output: int
request_throughput: float
input_throughput: float
output_throughput: float
token_throughput: float
mean_ttft_ms: float
median_ttft_ms: float
std_ttft_ms: float
Expand Down Expand Up @@ -283,8 +282,7 @@ def calculate_metrics(
total_input=total_input,
total_output=sum(actual_output_lens),
request_throughput=completed / dur_s,
input_throughput=total_input / dur_s,
output_throughput=sum(actual_output_lens) / dur_s,
token_throughput=(total_input + sum(actual_output_lens)) / dur_s,
mean_ttft_ms=np.mean(ttfts or 0) *
1000, # ttfts is empty if streaming is not supported by backend
std_ttft_ms=np.std(ttfts or 0) * 1000,
Expand Down Expand Up @@ -426,19 +424,16 @@ async def benchmark(
metrics.total_output))
print("{:<40} {:<10.2f}".format("Request throughput (req/s):",
metrics.request_throughput))
print("{:<40} {:<10.2f}".format("Input token throughput (tok/s):",
metrics.input_throughput))
print("{:<40} {:<10.2f}".format("Output token throughput (tok/s):",
metrics.output_throughput))
print("{:<40} {:<10.2f}".format("Token throughput (tok/s):",
metrics.token_throughput))

result = {
"duration": benchmark_duration,
"completed": metrics.completed,
"total_input_tokens": metrics.total_input,
"total_output_tokens": metrics.total_output,
"request_throughput": metrics.request_throughput,
"input_throughput": metrics.input_throughput,
"output_throughput": metrics.output_throughput,
"token_throughput": metrics.token_throughput,
"input_lens": [output.prompt_len for output in outputs],
"output_lens": actual_output_lens,
"ttfts": [output.ttft for output in outputs],
Expand Down
Loading