Add sanity check for max_running_requests (#5016)

fzyzcjy · web-flow · commit 5fc4b6004e84 · 2025-04-20T17:56:49.000-07:00
diff --git a/python/sglang/srt/managers/tp_worker.py b/python/sglang/srt/managers/tp_worker.py
@@ -116,6 +116,7 @@ def __init__(
             ),
             self.model_runner.req_to_token_pool.size,
         )
+        assert self.max_running_requests > 0, "max_running_request is zero"
         self.max_req_len = min(
             self.model_config.context_len - 1,
             self.max_total_num_tokens - 1,

Original file line number	Diff line number	Diff line change
`@@ -116,6 +116,7 @@ def __init__(`
`116`	`116`	`),`
`117`	`117`	`self.model_runner.req_to_token_pool.size,`
`118`	`118`	`)`
	`119`	`+ assert self.max_running_requests > 0, "max_running_request is zero"`
`119`	`120`	`self.max_req_len = min(`
`120`	`121`	`self.model_config.context_len - 1,`
`121`	`122`	`self.max_total_num_tokens - 1,`