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

Jump to bottom

When max-num-completed-requests is not divisible by num-concurrent-requests, an error will occur. #63

Open
huangdi614 opened this issue Aug 9, 2024 · 0 comments
Open

When max-num-completed-requests is not divisible by num-concurrent-requests, an error will occur. #63

huangdi614 opened this issue Aug 9, 2024 · 0 comments

Comments

@huangdi614
Copy link

Traceback (most recent call last):
File "token_benchmark_ray.py", line 463, in
run_token_benchmark(
File "token_benchmark_ray.py", line 304, in run_token_benchmark
summary, individual_responses = get_token_throughput_latencies(
File "token_benchmark_ray.py", line 99, in get_token_throughput_latencies
default_sampling_params = {"max_tokens": num_output_tokens_list.pop()}
IndexError: pop from empty list
huangdi614 pushed a commit to huangdi614/llmperf that referenced this issue Aug 9, 2024
fix issue ray-project#63
3672188
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@huangdi614