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 2, 03:30 UTC
[MRV2] Remove assignment of graph_pool in cudagraph_utils (#44338)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Woosuk Kwon committed
Jun 2, 2026 at 11:50 UTC
e4a2e584e56130f8318e85c1934c5be937d1e4e7
1 file changed
-1
vllm/v1/worker/gpu/cudagraph_utils.py
-1
@@ -299,7 +299,6 @@ class CudaGraphManager:
299
self.breakable_cg_runner = BreakableCUDAGraphWrapper(
300
model, self.vllm_config
301
)
302
- self.breakable_cg_runner.graph_pool = self.pool
302
303
def run_pw_graph(self, model: nn.Module, model_inputs: dict[str, Any]) -> Any:
304
if not self.use_breakable_cg: