[diffusion] feat: make scheduler rpc deadlines explicit (#33965)

Co-authored-by: suoyf <suoyf@nscc-tj.cn> Co-authored-by: Mick <mickjagger19@icloud.com>
2026-08-07 21:33:23 +08:00
parent bc8c037041
commit bc148dfdc8
9 changed files with 377 additions and 33 deletions
@@ -99,6 +99,7 @@ Use `sglang generate --help` and `sglang serve --help` for the full argument lis
 - `--srt-encoder-url {HTTPADDRESS}`: address of SGLang srt server with AR model for GLM-Image like models. See [Models with AR Stage](../models_with_ar).
 - `--srt-encoder-timeout {SECONDS}`: Timeout in seconds for HTTP requests to the SGLang encoder server
 - `--srt-encoder-connection-timeout {SECONDS}`: TCP connection timeout in seconds for SGLang encoder server
+- `--scheduler-rpc-timeout {SECONDS}`: optional end-to-end deadline for an internal scheduler RPC, including scheduler queue time. It is unset by default so valid long-running and queued video jobs are not failed by the transport layer. Set it only when the deployment requires a bounded request deadline; caller cancellation and server shutdown remain effective without it.
 - `--pe-server-url {HTTPADDRESS}`: url of SGLang server hosting the PE model (e.g., for ERNIE-Image). See [Models with Prompt Enhancement](../models_with_pe).

 ### Sampling and output