Unverified Commit 4839999b authored by fzyzcjy's avatar fzyzcjy Committed by GitHub
Browse files

Overlap two kernels in DeepSeek with communication (#6711)

parent 541a985f
...@@ -127,9 +127,9 @@ def _compute_moe_deepseek_blog_decode(layer): ...@@ -127,9 +127,9 @@ def _compute_moe_deepseek_blog_decode(layer):
layer.mlp.op_combine_a, layer.mlp.op_combine_a,
operations.YieldOperation(), operations.YieldOperation(),
layer.mlp.op_combine_b, layer.mlp.op_combine_b,
operations.YieldOperation(),
layer.mlp.op_output, layer.mlp.op_output,
layer.op_comm_postprocess_layer, layer.op_comm_postprocess_layer,
operations.YieldOperation(),
], ],
) )
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment