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 13, 00:45 UTC
[Minor] Rename `ec_producer` field to `is_ec_producer` (#28884)
Signed-off-by: Nick Hill <nhill@redhat.com>
Nick Hill committed
Nov 18, 2025 at 09:26 UTC
da8dadf68b5a2af849e7c5fd35ce9b8525d8d398
1 file changed
+2
-2
vllm/v1/engine/core.py
+2
-2
@@ -180,7 +180,7 @@ class EngineCore:
180
logger.info("Batch queue is enabled with size %d", self.batch_queue_size)
181
self.batch_queue = deque(maxlen=self.batch_queue_size)
182
183
- self.ec_producer = (
183
+ self.is_ec_producer = (
184
vllm_config.ec_transfer_config is not None
185
and vllm_config.ec_transfer_config.is_ec_producer
186
)
@@ -390,7 +390,7 @@ class EngineCore:
390
exec_future = self.model_executor.execute_model(
391
scheduler_output, non_block=True
392
)
393
- if not self.ec_producer:
393
+ if not self.is_ec_producer:
394
model_executed = scheduler_output.total_num_scheduled_tokens > 0
395
396
if self.is_pooling_model or not model_executed: