[Perf][Qwen] Replace MOE all-reduce with reduce-scatter (#47006)

Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Canlin Guo
2026-07-12 06:14:49 +00:00
committed by GitHub
co-authored by yewentao256
parent fc1c548093
commit a02984ed47
3 changed files with 113 additions and 11 deletions
@@ -437,6 +437,7 @@ class QwenGatedDeltaNetAttention(GatedDeltaNetAttention):
vllm_config: VllmConfig,
prefix: str = "",
gqa_interleaved_layout=False,
reduce_results: bool = True,
) -> None:
super().__init__(config, vllm_config, prefix)
@@ -547,6 +548,7 @@ class QwenGatedDeltaNetAttention(GatedDeltaNetAttention):
self.hidden_size,
bias=False,
input_is_parallel=True,
reduce_results=reduce_results,
quant_config=self.quant_config,
prefix=f"{prefix}.out_proj",
)