We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent fb410ee commit 35234ccCopy full SHA for 35234cc
xllm/core/layers/npu/npu_qwen3_moe_decoder_layer_impl.cpp
@@ -896,9 +896,7 @@ torch::Tensor NpuQwen3MoeDecoderLayerImpl::forward(
896
std::atomic<bool>* event_flag,
897
int node_id) {
898
atb::Status st;
899
- bool is_prefill = input_params.decode_seq_range.second !=
900
- input_params.q_seq_lens.size(0) - 1;
901
- if (is_prefill) {
+ if (!input_params.batch_forward_type.is_decode()) {
902
build_node_variant_pack(prefill_node_,
903
x,
904
cos_pos,
0 commit comments