Skip to content

Add tests for request latency metrics with remote prefill/decode #236

@mayabar

Description

@mayabar

Add tests for vllm:e2e_request_latency_seconds, vllm:request_prefill_time_seconds, vllm:request_decode_time_seconds that checks scenarios with remote prefill and decode

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions