Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion vllm_ascend/quantization/quant_config.py
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,8 @@ def get_quant_method(self, layer: torch.nn.Module,
elif isinstance(layer, FusedMoE):
if self.is_layer_skipped_ascend(prefix,
self.packed_modules_mapping):
return AscendUnquantizedFusedMoEMethod(layer.moe)
return AscendUnquantizedFusedMoEMethod(
layer.moe if hasattr(layer, 'moe') else None)
return AscendFusedMoEMethod(self, prefix,
self.packed_modules_mapping)
elif isinstance(layer, VocabParallelEmbedding):
Expand Down
3 changes: 0 additions & 3 deletions vllm_ascend/worker/model_runner_v1.py
Original file line number Diff line number Diff line change
Expand Up @@ -1154,9 +1154,6 @@ def _process_reqs(
attn_state,
total_num_scheduled_tokens)

enable_dbo = self._check_dbo_is_valid(self.query_lens.tolist(),
attn_state,
total_num_scheduled_tokens)
(padded_num_tokens_across_dp, num_tokens_across_dp, with_prefill,
enable_dbo) = self._get_forward_metadata_across_dp_and_pad(
total_num_scheduled_tokens, with_prefill, enable_dbo)
Expand Down
Loading