diff --git a/docs/run.md b/docs/run.md index c0b3cb78..0f4ab1eb 100644 --- a/docs/run.md +++ b/docs/run.md @@ -76,13 +76,13 @@ data: min: 10 # min length of the synthetic prompts max: 100 # max length of the synthetic prompts mean: 50 # mean length of the synthetic prompts - std: 10 # standard deviation of the length of the synthetic prompts + std_dev: 10 # standard deviation of the length of the synthetic prompts total_count: 100 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 100 # max length of the output to be generated mean: 50 # mean length of the output to be generated - std: 10 # standard deviation of the length of the output to be generated + std_dev: 10 # standard deviation of the length of the output to be generated total_count: 100 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: diff --git a/existing_stack/config_template.yaml b/existing_stack/config_template.yaml index 3dadcbf2..cf7fdfeb 100644 --- a/existing_stack/config_template.yaml +++ b/existing_stack/config_template.yaml @@ -51,13 +51,13 @@ workload: # yaml configuration for harness workload(s) min: 10 # min length of the synthetic prompts max: 100 # max length of the synthetic prompts mean: 50 # mean length of the synthetic prompts - std: 10 # standard deviation of the length of the synthetic prompts + std_dev: 10 # standard deviation of the length of the synthetic prompts total_count: 100 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 100 # max length of the output to be generated mean: 50 # mean length of the output to be generated - std: 10 # standard deviation of the length of the output to be generated + std_dev: 10 # standard deviation of the length of the output to be generated total_count: 100 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: diff --git a/workload/profiles/inference-perf/chatbot_synthetic.yaml.in b/workload/profiles/inference-perf/chatbot_synthetic.yaml.in index d2a1022a..94a26464 100644 --- a/workload/profiles/inference-perf/chatbot_synthetic.yaml.in +++ b/workload/profiles/inference-perf/chatbot_synthetic.yaml.in @@ -25,13 +25,13 @@ data: min: 10 # min length of the synthetic prompts max: 8192 # max length of the synthetic prompts mean: 4096 # mean length of the synthetic prompts - std: 2048 # standard deviation of the length of the synthetic prompts + std_dev: 2048 # standard deviation of the length of the synthetic prompts total_count: 1000 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 2048 # max length of the output to be generated mean: 1024 # mean length of the output to be generated - std: 512 # standard deviation of the length of the output to be generated + std_dev: 512 # standard deviation of the length of the output to be generated total_count: 1000 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: diff --git a/workload/profiles/inference-perf/code_completion_synthetic.yaml.in b/workload/profiles/inference-perf/code_completion_synthetic.yaml.in index 900c9843..acf5383f 100644 --- a/workload/profiles/inference-perf/code_completion_synthetic.yaml.in +++ b/workload/profiles/inference-perf/code_completion_synthetic.yaml.in @@ -25,13 +25,13 @@ data: min: 10 # min length of the synthetic prompts max: 4096 # max length of the synthetic prompts mean: 2048 # mean length of the synthetic prompts - std: 1024 # standard deviation of the length of the synthetic prompts + std_dev: 1024 # standard deviation of the length of the synthetic prompts total_count: 1000 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 256 # max length of the output to be generated mean: 128 # mean length of the output to be generated - std: 64 # standard deviation of the length of the output to be generated + std_dev: 64 # standard deviation of the length of the output to be generated total_count: 1000 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: diff --git a/workload/profiles/inference-perf/sanity_random.yaml.in b/workload/profiles/inference-perf/sanity_random.yaml.in index 51e8beec..03653a67 100644 --- a/workload/profiles/inference-perf/sanity_random.yaml.in +++ b/workload/profiles/inference-perf/sanity_random.yaml.in @@ -19,13 +19,13 @@ data: min: 10 # min length of the synthetic prompts max: 100 # max length of the synthetic prompts mean: 50 # mean length of the synthetic prompts - std: 10 # standard deviation of the length of the synthetic prompts + std_dev: 10 # standard deviation of the length of the synthetic prompts total_count: 100 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 100 # max length of the output to be generated mean: 50 # mean length of the output to be generated - std: 10 # standard deviation of the length of the output to be generated + std_dev: 10 # standard deviation of the length of the output to be generated total_count: 100 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: diff --git a/workload/profiles/inference-perf/summarization_synthetic.yaml.in b/workload/profiles/inference-perf/summarization_synthetic.yaml.in index f3dcd7a2..c56ffdd7 100644 --- a/workload/profiles/inference-perf/summarization_synthetic.yaml.in +++ b/workload/profiles/inference-perf/summarization_synthetic.yaml.in @@ -25,13 +25,13 @@ data: min: 10 # min length of the synthetic prompts max: 4096 # max length of the synthetic prompts mean: 2048 # mean length of the synthetic prompts - std: 1024 # standard deviation of the length of the synthetic prompts + std_dev: 1024 # standard deviation of the length of the synthetic prompts total_count: 1000 # total number of prompts to generate to fit the above mentioned distribution constraints output_distribution: min: 10 # min length of the output to be generated max: 512 # max length of the output to be generated mean: 256 # mean length of the output to be generated - std: 128 # standard deviation of the length of the output to be generated + std_dev: 128 # standard deviation of the length of the output to be generated total_count: 1000 # total number of output lengths to generate to fit the above mentioned distribution constraints report: request_lifecycle: