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, 04:45 UTC
[Perf] Improved perf for resolve_chat_template_content_format (#20065)
Signed-off-by: Ilya Lavrenov <ilya.lavrenov@cerebras.net>
Ilya Lavrenov committed
Jun 27, 2025 at 13:16 UTC
aa0dc77ef53b365ddf54be51748c166895a0bcd9
1 file changed
+1
vllm/entrypoints/chat_utils.py
+1
@@ -293,6 +293,7 @@ def _try_extract_ast(chat_template: str) -> Optional[jinja2.nodes.Template]:
293
return None
294
295
296
+@lru_cache(maxsize=32)
297
def _detect_content_format(
298
chat_template: str,
299
*,