Reference documentation and code samples for the GKE Recommender V1 API class Google::Cloud::GkeRecommender::V1::PerformanceRequirements.
Performance requirements for a profile and or model deployment.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#target_cost
def target_cost() -> ::Google::Cloud::GkeRecommender::V1::Cost
Returns
- (::Google::Cloud::GkeRecommender::V1::Cost) — Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.
#target_cost=
def target_cost=(value) -> ::Google::Cloud::GkeRecommender::V1::Cost
Parameter
- value (::Google::Cloud::GkeRecommender::V1::Cost) — Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.
Returns
- (::Google::Cloud::GkeRecommender::V1::Cost) — Optional. The target cost for running a profile's model server. If not provided, this requirement will not be enforced.
#target_ntpot_milliseconds
def target_ntpot_milliseconds() -> ::Integer
Returns
-
(::Integer) — Optional. The target Normalized Time Per Output Token (NTPOT) in
milliseconds. NTPOT is calculated as
request_latency / total_output_tokens. If not provided, this target will not be enforced.
#target_ntpot_milliseconds=
def target_ntpot_milliseconds=(value) -> ::Integer
Parameter
-
value (::Integer) — Optional. The target Normalized Time Per Output Token (NTPOT) in
milliseconds. NTPOT is calculated as
request_latency / total_output_tokens. If not provided, this target will not be enforced.
Returns
-
(::Integer) — Optional. The target Normalized Time Per Output Token (NTPOT) in
milliseconds. NTPOT is calculated as
request_latency / total_output_tokens. If not provided, this target will not be enforced.
#target_ttft_milliseconds
def target_ttft_milliseconds() -> ::Integer
Returns
- (::Integer) — Optional. The target Time To First Token (TTFT) in milliseconds. TTFT is the time it takes to generate the first token for a request. If not provided, this target will not be enforced.
#target_ttft_milliseconds=
def target_ttft_milliseconds=(value) -> ::Integer
Parameter
- value (::Integer) — Optional. The target Time To First Token (TTFT) in milliseconds. TTFT is the time it takes to generate the first token for a request. If not provided, this target will not be enforced.
Returns
- (::Integer) — Optional. The target Time To First Token (TTFT) in milliseconds. TTFT is the time it takes to generate the first token for a request. If not provided, this target will not be enforced.