EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[Bugfix] Resolve the interface compatibility issue of get_input_embeddings in MM (#4638)

Browse Source 
### What this PR does / why we need it?
Resolve the interface compatibility issue of get_input_embeddings in MM，
because the get_input_embeddings func of other model does not have the
is_multimodal parameter

---------

Signed-off-by: Levi-JQ <yujinqi2@huawei.com>
Co-authored-by: Levi-JQ <yujinqi2@huawei.com>
This commit is contained in:
Levi
2025-12-02 22:21:47 +08:00
committed by GitHub
parent 3b4cb23616
commit 865f1f7fc8
1 changed files with 13 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vllm_ascend/worker/model_runner_v1.py
View File

@@ -1394,11 +1394,19 @@ class NPUModelRunner(LoRAModelRunnerMixin):
# embeddings), we always use embeddings (rather than token ids) # embeddings), we always use embeddings (rather than token ids)
# as input to the multimodal model, even when the input is text. # as input to the multimodal model, even when the input is text.
input_ids = self.input_ids[:total_num_scheduled_tokens] input_ids = self.input_ids[:total_num_scheduled_tokens]
inputs_embeds = self.model.get_input_embeddings( model_type = self.vllm_config.model_config.hf_config.model_type
input_ids, if model_type == "qwen2_5_vl":
multimodal_embeddings=mm_embeds, inputs_embeds = self.model.get_input_embeddings(
is_multimodal=is_mm_embed, input_ids,
) multimodal_embeddings=mm_embeds,
is_multimodal=is_mm_embed,
)
else:
if mm_embeds:
inputs_embeds = self.model.get_input_embeddings(
input_ids, mm_embeds)
else:
inputs_embeds = self.model.get_input_embeddings(input_ids)
# TODO(woosuk): Avoid the copy. Optimize. # TODO(woosuk): Avoid the copy. Optimize.
self.inputs_embeds[:total_num_scheduled_tokens].copy_( self.inputs_embeds[:total_num_scheduled_tokens].copy_(
inputs_embeds) inputs_embeds)