whisper: Current attn type {attn_type} is not implemented for IpexAttnBackendImpl #41
Description
Following https://github.com/intel/llm-scaler/tree/main/vllm#241-audio-model-support to run whisper, resulted in below error.
Traceback (most recent call last):
File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 459, in run_mp_engine
raise e from None
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 445, in run_mp_engine
engine = MQLLMEngine.from_vllm_config(
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 132, in from_vllm_config
return cls(
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/multiprocessing/engine.py", line 86, in __init__
self.engine = LLMEngine(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/engine/llm_engine.py", line 265, in __init__
self.model_executor = executor_class(vllm_config=vllm_config)
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/executor_base.py", line 52, in __init__
self._init_executor()
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/uniproc_executor.py", line 47, in _init_executor
self.collective_rpc("load_model")
File "/usr/local/lib/python3.10/dist-packages/vllm/executor/uniproc_executor.py", line 56, in collective_rpc
answer = run_method(self.driver_worker, method, args, kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/utils.py", line 2611, in run_method
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/vllm/worker/worker.py", line 207, in load_model
self.model_runner.load_model()
File "/usr/local/lib/python3.10/dist-packages/vllm/worker/xpu_model_runner.py", line 808, in load_model
self.model = get_model(vllm_config=self.vllm_config)
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/__init__.py", line 58, in get_model
return loader.load_model(vllm_config=vllm_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/default_loader.py", line 273, in load_model
model = initialize_model(vllm_config=vllm_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/model_loader/utils.py", line 63, in initialize_model
return model_class(vllm_config=vllm_config, prefix=prefix)
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 661, in __init__
self.model = WhisperModel(vllm_config=vllm_config, prefix=prefix)
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 456, in __init__
self.encoder = WhisperEncoder(vllm_config=vllm_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 373, in __init__
self.start_layer, self.end_layer, self.layers = make_layers(
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/utils.py", line 625, in make_layers
[PPMissingLayer() for _ in range(start_layer)] + [
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/utils.py", line 626, in <listcomp>
maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}"))
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 375, in <lambda>
lambda prefix: WhisperEncoderLayer(vllm_config=vllm_config,
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 255, in __init__
self.self_attn = WhisperAttention(
File "/usr/local/lib/python3.10/dist-packages/vllm/model_executor/models/whisper.py", line 104, in __init__
self.attn = Attention(
File "/usr/local/lib/python3.10/dist-packages/vllm/attention/layer.py", line 134, in __init__
self.impl = impl_cls(num_heads, head_size, scale, num_kv_heads,
File "/usr/local/lib/python3.10/dist-packages/vllm/attention/backends/ipex_attn.py", line 165, in __init__
raise NotImplementedError("Current attn type {attn_type} " \
NotImplementedError: Current attn type {attn_type} is not implemented for IpexAttnBackendImpl