We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 054add2 commit c55f2e0Copy full SHA for c55f2e0
1 file changed
fastdeploy/model_executor/models/qwen3_vl/qwen3_vl.py
@@ -381,6 +381,10 @@ def forward(
381
382
return hidden_states
383
384
+ def clear_grpah_opt_backend(self):
385
+ """Clear graph optimization backend, the captured cuda graph will be cleaned"""
386
+ self.model.clear_grpah_opt_backend(fd_config=self.fd_config)
387
+
388
389
class Qwen3VLPretrainedModel(PretrainedModel):
390
"""Utilities for tensor-parallel weight splitting."""
0 commit comments