Class: Google::Cloud::GkeRecommender::V1::PerformanceRange

Inherits:
Object
  • Object
show all
Extended by:
Protobuf::MessageExts::ClassMethods
Includes:
Protobuf::MessageExts
Defined in:
proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb

Overview

Performance range for a model deployment.

Instance Attribute Summary collapse

Instance Attribute Details

#ntpot_range ⇒ ::Google::Cloud::GkeRecommender::V1::MillisecondRange (readonly)

Returns Output only. The range of NTPOT (Normalized Time Per Output Token) in milliseconds. NTPOT is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.

Returns:

  • (::Google::Cloud::GkeRecommender::V1::MillisecondRange) —

    Output only. The range of NTPOT (Normalized Time Per Output Token) in milliseconds. NTPOT is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.



351
352
353
354
 
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 351

class PerformanceRange
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#throughput_output_range ⇒ ::Google::Cloud::GkeRecommender::V1::TokensPerSecondRange (readonly)

Returns Output only. The range of throughput in output tokens per second. This is measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.

Returns:



351
352
353
354
 
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 351

class PerformanceRange
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end

#ttft_range ⇒ ::Google::Cloud::GkeRecommender::V1::MillisecondRange (readonly)

Returns Output only. The range of TTFT (Time To First Token) in milliseconds. TTFT is the time it takes to generate the first token for a request.

Returns:



351
352
353
354
 
# File 'proto_docs/google/cloud/gkerecommender/v1/gkerecommender.rb', line 351

class PerformanceRange
  include ::Google::Protobuf::MessageExts
  extend ::Google::Protobuf::MessageExts::ClassMethods
end