[Fix] Add _MOE_TP to graph_capture for MoE models with ep>1 (#21907)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
This commit is contained in:
co-authored by
Claude Opus 4.6
Baizhou Zhang
parent
ac593fed90
commit
56ac9c9932
@@ -1133,6 +1133,9 @@ class ServerArgs:
|
||||
# 16. Expert distribution recorder
|
||||
if self.enable_eplb or self.expert_distribution_recorder_mode is not None:
|
||||
self.disable_piecewise_cuda_graph = True
|
||||
# 17. Context parallel
|
||||
if self.attn_cp_size > 1:
|
||||
self.disable_piecewise_cuda_graph = True
|
||||
|
||||
def _handle_gpu_memory_settings(self, gpu_mem):
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user