Reference documentation and code samples for the GKE Recommender V1 API class Google::Cloud::GkeRecommender::V1::PerformanceStats.
Performance statistics for a model deployment.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#cost
def cost() -> ::Array<::Google::Cloud::GkeRecommender::V1::Cost>
Returns
- (::Array<::Google::Cloud::GkeRecommender::V1::Cost>) — Output only. The cost of running the model deployment.
#ntpot_milliseconds
def ntpot_milliseconds() -> ::Integer
Returns
- (::Integer) — Output only. The Normalized Time Per Output Token (NTPOT) in milliseconds. This is the request latency normalized by the number of output tokens, measured as request_latency / total_output_tokens.
#output_tokens_per_second
def output_tokens_per_second() -> ::Integer
Returns
- (::Integer) — Output only. The number of output tokens per second. This is the throughput measured as total_output_tokens_generated_by_server / elapsed_time_in_seconds.
#queries_per_second
def queries_per_second() -> ::Float
Returns
- (::Float) — Output only. The number of queries per second. Note: This metric can vary widely based on context length and may not be a reliable measure of LLM throughput.
#ttft_milliseconds
def ttft_milliseconds() -> ::Integer
Returns
- (::Integer) — Output only. The Time To First Token (TTFT) in milliseconds. This is the time it takes to generate the first token for a request.