[Metrics] Add audio SLOs + cross-stage transfer families + per-(stage, replica) wrap for upstream vllm:* (#3576)

Signed-off-by: vraiti <vraiti@redhat.com>
Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Co-authored-by: vraiti <vraiti@redhat.com>
This commit is contained in:
LHXuuuandvraiti authored and GitHub committed 2026-06-01 20:20:48 +08:00
1 parent ee33601571
commit 41a795b5d6
29 files changed
+3377 -25

No files matched your search

+4
View File
@@ -13,6 +13,10 @@ This section contains design documents and architecture specifications for vLLM-
- [Adding Step Execution Support for Diffusion Pipelines](feature/diffusion_step_execution.md)
- [Continuous Batching for Step-Wise Diffusion](feature/diffusion_continuous_batching.md)
## Infrastructure Design Documents
- [Prometheus Metrics](metrics.md)
## Module Design Documents
- [AR Module](module/ar_module.md)