resemble-ai
[Bug] Cuda Error: CUBLAS_STATUS_NOT_SUPPORTED
Hello, So I just installed chatterbox and when I tried to generate some speech I get the error in the title saying Cublas is not supported. From my understanding chatterbox is usable on amd and invidia and since I'm on amd it should auto detect that I'm using zluda so I'm not understanding why I'm getting that error. It it something I can fix or is chatterbox not compatible with amd/zluda.
Entire error message for reference -
This share link expires in 1 week. For free permanent hosting and GPU upgrades, run gradio deploy from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)
C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\models\lora.py:393: FutureWarning: LoRACompatibleLinear is deprecated and will be removed in version 1.0.0. Use of LoRACompatibleLinear is deprecated. Please switch to PEFT backend by installing PEFT: pip install peft.
deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
loaded PerthNet (Implicit) at step 250,000
loaded PerthNet (Implicit) at step 250,000
Traceback (most recent call last):
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\queueing.py", line 626, in process_events
response = await route_utils.call_process_api(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\route_utils.py", line 350, in call_process_api
output = await app.get_blocks().process_api(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 2235, in process_api
result = await self.call_function(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\blocks.py", line 1746, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 2470, in run_sync_in_worker_thread
return await future
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\anyio_backends_asyncio.py", line 967, in run
result = context.run(func, *args)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\utils.py", line 917, in wrapper
response = f(*args, **kwargs)
File "K:\chatterbox\chatterbox-master\chatterbox-master\gradio_tts_app.py", line 31, in generate
wav = model.generate(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\chatterbox\tts.py", line 246, in generate
speech_tokens = self.t3.inference(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\chatterbox\models\t3\t3.py", line 240, in inference
embeds, len_cond = self.prepare_input_embeds(
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\chatterbox\models\t3\t3.py", line 89, in prepare_input_embeds
cond_emb = self.prepare_conditioning(t3_cond) # (B, len_cond, dim)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\chatterbox\models\t3\t3.py", line 78, in prepare_conditioning
return self.cond_enc(t3_cond) # (B, len_cond, dim)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\chatterbox\models\t3\modules\cond_enc.py", line 70, in forward
cond_spkr = self.spkr_enc(cond.speaker_emb.view(-1, self.hp.speaker_embed_size))[:, None] # (B, 1, dim)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\Ezra\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\linear.py", line 125, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling cublasLtMatmulAlgoGetHeuristic( ltHandle, computeDesc.descriptor(), Adesc.descriptor(), Bdesc.descriptor(), Cdesc.descriptor(), Cdesc.descriptor(), preference.descriptor(), 1, &heuristicResult, &returnedResult)
