Allow AsyncLLMEngine.generate to target a specific DP rank (#19102)

Signed-off-by: Jon Swenson <jmswen@gmail.com>
2025-06-04 08:26:47 -07:00
parent 8f4ffbd373
commit c8dcc15921
10 changed files with 97 additions and 5 deletions
--- a/tests/tokenization/test_detokenize.py
+++ b/tests/tokenization/test_detokenize.py
@@ -70,7 +70,8 @@ def _run_incremental_decode(tokenizer,
                                None,
                                0.0,
                                None,
-                                cache_salt=None)
+                                cache_salt=None,
+                                data_parallel_rank=None)

    if fast is None:
        detokenizer = IncrementalDetokenizer.from_new_request(