diff --git a/src/megatron/bridge/inference/_tokenizer.py b/src/megatron/bridge/inference/_tokenizer.py
index b1e3873d73..5ec33be81f 100644
--- a/src/megatron/bridge/inference/_tokenizer.py
+++ b/src/megatron/bridge/inference/_tokenizer.py
@@ -46,6 +46,11 @@ def __init__(
     ) -> None:
         self._tokenizer = tokenizer
         self._force_skip_special_tokens = force_skip_special_tokens
+        # MCore's incremental detokenizer treats ``_tokenizer`` as its Hugging Face wrapper.
+        if not hasattr(tokenizer, "tokenizer"):
+            tokenizer.tokenizer = tokenizer
+        if not hasattr(tokenizer, "include_special_tokens"):
+            tokenizer.include_special_tokens = force_skip_special_tokens is False
         if set_pad_token and tokenizer.pad_token is None and tokenizer.eos_token is not None:
             tokenizer.pad_token = tokenizer.eos_token
         self.eod = tokenizer.eos_token_id
diff --git a/tests/unit_tests/inference/test_tokenizer.py b/tests/unit_tests/inference/test_tokenizer.py
index d0f626e745..68af3f3a72 100644
--- a/tests/unit_tests/inference/test_tokenizer.py
+++ b/tests/unit_tests/inference/test_tokenizer.py
@@ -16,6 +16,12 @@
 
 from __future__ import annotations
 
+from megatron.core.inference.text_generation_server.dynamic_text_gen_server.incremental_detokenizer import (
+    HuggingFaceFastIncrementalDetokenizer,
+)
+from tokenizers import Tokenizer, models
+from transformers import PreTrainedTokenizerFast
+
 from megatron.bridge.inference._tokenizer import HFTokenizerAdapter
 
 
@@ -119,3 +125,14 @@ def test_openai_server_preserves_hf_chat_template_contract():
             },
         )
     ]
+
+
+def test_openai_streaming_accepts_hf_fast_tokenizer_adapter():
+    backend = Tokenizer(models.WordLevel(vocab={"[UNK]": 0, "hello": 1}, unk_token="[UNK]"))
+    tokenizer = PreTrainedTokenizerFast(tokenizer_object=backend, unk_token="[UNK]", eos_token="[UNK]")
+    adapter = HFTokenizerAdapter(tokenizer)
+
+    detokenizer = HuggingFaceFastIncrementalDetokenizer(adapter, [])
+
+    assert detokenizer.text == ""
+    assert detokenizer.update([tokenizer.eos_token_id]) == ""