feat(frontend): session id plumbing into requests (#48048)

Signed-off-by: Karen Chung <karenc@nvidia.com>
This commit is contained in:
Karen Chung
2026-08-03 22:18:58 +00:00
committed by GitHub
parent e578de311c
commit f57123aa2d
39 changed files with 438 additions and 4 deletions
+2
View File
@@ -225,6 +225,7 @@ class LLMEngine:
tokenization_kwargs: dict[str, Any] | None = None,
trace_headers: Mapping[str, str] | None = None,
priority: int = 0,
session_id: str | None = None,
prompt_text: str | None = None,
) -> str:
# Validate the request_id type.
@@ -257,6 +258,7 @@ class LLMEngine:
tokenization_kwargs=tokenization_kwargs,
trace_headers=trace_headers,
priority=priority,
session_id=session_id,
)
prompt_text, _, _ = extract_prompt_components(self.model_config, prompt)