[Metrics] Complete removal of deprecated vllm:time_per_output_token_seconds metric (#32661)
This PR completes the removal of the deprecated vllm:time_per_output_token_seconds metric that was deprecated in v0.11, hidden in v0.12, scheduled for removal in v0.13, but delayed until v0.15. Signed-off-by: carlory <baofa.fan@daocloud.io> Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Haiku 4.5
parent
c4e5bdf61b
commit
bb9172030e
@@ -77,7 +77,7 @@ def _get_expected_values(num_requests: int, prompt_ids: list[int], max_tokens: i
|
||||
# {metric_family: [(suffix, expected_value)]}
|
||||
return {
|
||||
"vllm:time_to_first_token_seconds": [("_count", num_requests)],
|
||||
"vllm:time_per_output_token_seconds": [
|
||||
"vllm:inter_token_latency_seconds": [
|
||||
("_count", num_requests * (max_tokens - 1))
|
||||
],
|
||||
"vllm:e2e_request_latency_seconds": [("_count", num_requests)],
|
||||
@@ -203,9 +203,6 @@ EXPECTED_METRICS_V1 = [
|
||||
"vllm:request_params_max_tokens_sum",
|
||||
"vllm:request_params_max_tokens_bucket",
|
||||
"vllm:request_params_max_tokens_count",
|
||||
"vllm:time_per_output_token_seconds_sum",
|
||||
"vllm:time_per_output_token_seconds_bucket",
|
||||
"vllm:time_per_output_token_seconds_count",
|
||||
"vllm:time_to_first_token_seconds_sum",
|
||||
"vllm:time_to_first_token_seconds_bucket",
|
||||
"vllm:time_to_first_token_seconds_count",
|
||||
@@ -238,9 +235,6 @@ HIDDEN_DEPRECATED_METRICS: list[str] = [
|
||||
"vllm:gpu_cache_usage_perc",
|
||||
"vllm:gpu_prefix_cache_queries",
|
||||
"vllm:gpu_prefix_cache_hits",
|
||||
"vllm:time_per_output_token_seconds_sum",
|
||||
"vllm:time_per_output_token_seconds_bucket",
|
||||
"vllm:time_per_output_token_seconds_count",
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user