Skip to content

Commit f458cc5

Browse files
carryyuEmmonsCurse
andauthored
[Optimization]1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM (#5353)
* [Optimization] 1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM * fix test_chunked_moe --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
1 parent 04d35ac commit f458cc5

File tree

1 file changed

+1
-0
lines changed

1 file changed

+1
-0
lines changed

tests/distributed/chunked_moe.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -138,6 +138,7 @@ def setup_fused_moe(self):
138138
fused_moe = FusedMoE.__new__(FusedMoE)
139139
fused_moe.ep_size = 2
140140
fused_moe.tp_size = 1
141+
fused_moe.attn_tp_size = 1
141142
fused_moe.reduce_results = True
142143

143144
fused_moe.fd_config = mock_fd_config

0 commit comments

Comments
 (0)