A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 09:45 UTC
[Fix] Fix typo in `resolve_hf_chat_template` (#18259)
Signed-off-by: Felix Marty <felmarty@amd.com>
fxmarty-amd committed
May 16, 2025 at 16:52 UTC
a5f8c111c261f43726f24fcd56f450c0567bff8b
1 file changed
+2
-2
vllm/entrypoints/chat_utils.py
+2
-2
@@ -339,7 +339,7 @@ def resolve_hf_chat_template(
339
tools: Optional[list[dict[str, Any]]],
340
*,
341
model_config: ModelConfig,
342
- trsut_remote_code: Optional[bool] = None,
342
+ trust_remote_code: Optional[bool] = None,
343
) -> Optional[str]:
344
# 1st priority: The given chat template
345
if chat_template is not None:
@@ -1293,4 +1293,4 @@ def apply_mistral_chat_template(
1293
raise ValueError from e
1294
1295
def random_tool_call_id() -> str:
1296
- return f"chatcmpl-tool-{random_uuid()}"
\ No newline at end of file
1296
+ return f"chatcmpl-tool-{random_uuid()}"