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 16, 10:45 UTC
[Core] Fix invalid args to _process_request (#9201)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Russell Bryant committed
Oct 10, 2024 at 00:10 UTC
cf25b93bddb607077e52cbe4681332ca61aff189
1 file changed
+2
-1
vllm/engine/multiprocessing/client.py
+2
-1
@@ -606,7 +606,8 @@ class MQLLMEngineClient:
606
and request_id is not None)
607
608
return self._process_request(prompt, pooling_params, request_id,
609
- lora_request, trace_headers, priority)
609
+ lora_request, trace_headers, None,
610
+ priority)
611
612
async def _process_request(
613
self,