karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[Model Runner V2] Fix v2 AttributeError: 'CohereASRDecoder' object has no attribute 'embed_input_ids' (#44568)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Wentao Ye
2026-06-10 11:06:01 -07:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent bfe1001ab6
commit ffce72c041
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/v1/worker/gpu/model_states/__init__.py
+4 -1
View File
@@ -13,7 +13,10 @@ def init_model_state(
encoder_cache: EncoderCache | None,
device: torch.device,
):
if "WhisperForConditionalGeneration" in vllm_config.model_config.architectures:
if (
"WhisperForConditionalGeneration" in vllm_config.model_config.architectures
or "CohereAsrForConditionalGeneration" in vllm_config.model_config.architectures
):
from vllm.v1.worker.gpu.model_states.whisper import WhisperModelState
return WhisperModelState(vllm_config, model, encoder_cache, device)