A high-throughput and memory-efficient inference and serving engine for LLMs
[Bugfix] Add X-Session-ID from conversation_id in multi-turn benchmark (#44663)
Signed-off-by: Tyko Niemi <tyko.niemi@amd.com>
Tyko Niemi committed
Jun 9, 2026 at 18:57 UTC
cad4ca12b89523793b009129d954492fdcaf1026
1 file changed
+2
benchmarks/multi_turn/benchmark_serving_multi_turn.py
+2
@@ -240,6 +240,8 @@ async def send_request(
240
payload["max_tokens"] = max_tokens
241
242
headers = {"Content-Type": "application/json"}
243
+ if conversation_id is not None:
244
+ headers["X-Session-ID"] = str(conversation_id)
245
246
# Calculate the timeout for the request
247
if max_tokens is not None: