text-generation-inference icon indicating copy to clipboard operation
text-generation-inference copied to clipboard

Nightly load test results

Open Hugoch opened this issue 1 year ago • 4 comments

This issue collects load test results runs on nightly builds.

Hugoch avatar Jul 15 '24 18:07 Hugoch

🚀 Load test results are in for commit bee5616cfc2a93e721bfc06a58bebf13f85cae45

Variable length prompts

Constant length prompts

Delta to last release

Metric Input Type Test Type Avg Delta (%)
requests_ok sharegpt_conversations constant_vus 0
error_rate sharegpt_conversations constant_vus 0
end_to_end_latency sharegpt_conversations constant_vus 0
inter_token_latency sharegpt_conversations constant_vus 0
time_to_first_token sharegpt_conversations constant_vus 0
tokens_throughput sharegpt_conversations constant_vus 0
requests_ok sharegpt_conversations constant_arrival_rate 0
error_rate sharegpt_conversations constant_arrival_rate 0
end_to_end_latency sharegpt_conversations constant_arrival_rate 0
inter_token_latency sharegpt_conversations constant_arrival_rate 0
time_to_first_token sharegpt_conversations constant_arrival_rate 0
tokens_throughput sharegpt_conversations constant_arrival_rate 0
requests_ok constant_tokens constant_vus 0
error_rate constant_tokens constant_vus 0
end_to_end_latency constant_tokens constant_vus 0
inter_token_latency constant_tokens constant_vus 0
time_to_first_token constant_tokens constant_vus 0
tokens_throughput constant_tokens constant_vus 0
requests_ok constant_tokens constant_arrival_rate 0
error_rate constant_tokens constant_arrival_rate 0
end_to_end_latency constant_tokens constant_arrival_rate 0
inter_token_latency constant_tokens constant_arrival_rate 0
time_to_first_token constant_tokens constant_arrival_rate 0
tokens_throughput constant_tokens constant_arrival_rate 0

github-actions[bot] avatar Jul 16 '24 15:07 github-actions[bot]

🚀 Load test results are in for commit ceac61a0267331875b355fd439c091c77fff139f

Variable length prompts

Constant length prompts

Delta to last release

Metric Input Type Test Type Avg Delta (%)
requests_ok sharegpt_conversations constant_vus 0
error_rate sharegpt_conversations constant_vus 0
end_to_end_latency sharegpt_conversations constant_vus 0
inter_token_latency sharegpt_conversations constant_vus 0
time_to_first_token sharegpt_conversations constant_vus 0
tokens_throughput sharegpt_conversations constant_vus 0
requests_ok sharegpt_conversations constant_arrival_rate 0
error_rate sharegpt_conversations constant_arrival_rate 0
end_to_end_latency sharegpt_conversations constant_arrival_rate 0
inter_token_latency sharegpt_conversations constant_arrival_rate 0
time_to_first_token sharegpt_conversations constant_arrival_rate 0
tokens_throughput sharegpt_conversations constant_arrival_rate 0
requests_ok constant_tokens constant_vus 0
error_rate constant_tokens constant_vus 0
end_to_end_latency constant_tokens constant_vus 0
inter_token_latency constant_tokens constant_vus 0
time_to_first_token constant_tokens constant_vus 0
tokens_throughput constant_tokens constant_vus 0
requests_ok constant_tokens constant_arrival_rate 0
error_rate constant_tokens constant_arrival_rate 0
end_to_end_latency constant_tokens constant_arrival_rate 0
inter_token_latency constant_tokens constant_arrival_rate 0
time_to_first_token constant_tokens constant_arrival_rate 0
tokens_throughput constant_tokens constant_arrival_rate 0

github-actions[bot] avatar Jul 18 '24 09:07 github-actions[bot]

🚀 Load test results are in for commit 893bd3c924c341a3b7a1c53a5a6bd3379501bd2d

Variable length prompts

Constant length prompts

Delta to last release

Metric Input Type Test Type Avg Delta (%)
requests_ok sharegpt_conversations constant_vus 0
error_rate sharegpt_conversations constant_vus 0
end_to_end_latency sharegpt_conversations constant_vus 0
inter_token_latency sharegpt_conversations constant_vus 0
time_to_first_token sharegpt_conversations constant_vus 0
tokens_throughput sharegpt_conversations constant_vus 0
requests_ok sharegpt_conversations constant_arrival_rate 0
error_rate sharegpt_conversations constant_arrival_rate 0
end_to_end_latency sharegpt_conversations constant_arrival_rate 0
inter_token_latency sharegpt_conversations constant_arrival_rate 0
time_to_first_token sharegpt_conversations constant_arrival_rate 0
tokens_throughput sharegpt_conversations constant_arrival_rate 0
requests_ok constant_tokens constant_vus 0
error_rate constant_tokens constant_vus 0
end_to_end_latency constant_tokens constant_vus 0
inter_token_latency constant_tokens constant_vus 0
time_to_first_token constant_tokens constant_vus 0
tokens_throughput constant_tokens constant_vus 0
requests_ok constant_tokens constant_arrival_rate 0
error_rate constant_tokens constant_arrival_rate 0
end_to_end_latency constant_tokens constant_arrival_rate 0
inter_token_latency constant_tokens constant_arrival_rate 0
time_to_first_token constant_tokens constant_arrival_rate 0
tokens_throughput constant_tokens constant_arrival_rate 0

github-actions[bot] avatar Aug 02 '24 14:08 github-actions[bot]

🚀 Load test results are in for commit 4e7c0c63c6d2a671ff2306a84212aeb339f1e92b

Variable length prompts

Constant length prompts

Delta to last release

Metric Input Type Test Type Avg Delta (%)
requests_ok sharegpt_conversations constant_vus 0
error_rate sharegpt_conversations constant_vus 0
end_to_end_latency sharegpt_conversations constant_vus 0
inter_token_latency sharegpt_conversations constant_vus 0
time_to_first_token sharegpt_conversations constant_vus 0
tokens_throughput sharegpt_conversations constant_vus 0
requests_ok sharegpt_conversations constant_arrival_rate 0
error_rate sharegpt_conversations constant_arrival_rate 0
end_to_end_latency sharegpt_conversations constant_arrival_rate 0
inter_token_latency sharegpt_conversations constant_arrival_rate 0
time_to_first_token sharegpt_conversations constant_arrival_rate 0
tokens_throughput sharegpt_conversations constant_arrival_rate 0
requests_ok constant_tokens constant_vus 0
error_rate constant_tokens constant_vus 0
end_to_end_latency constant_tokens constant_vus 0
inter_token_latency constant_tokens constant_vus 0
time_to_first_token constant_tokens constant_vus 0
tokens_throughput constant_tokens constant_vus 0
requests_ok constant_tokens constant_arrival_rate 0
error_rate constant_tokens constant_arrival_rate 0
end_to_end_latency constant_tokens constant_arrival_rate 0
inter_token_latency constant_tokens constant_arrival_rate 0
time_to_first_token constant_tokens constant_arrival_rate 0
tokens_throughput constant_tokens constant_arrival_rate 0

github-actions[bot] avatar Sep 02 '24 09:09 github-actions[bot]