Exception: cublasLt ran into an error!

[touhi99]

I am running on Ubuntu 22.04 with a 8GB GPU

The error as follows when giving the prompt:

cuBLAS API failed with status 15
A: torch.Size([24, 4096]), B: torch.Size([4096, 4096]), C: (24, 4096); (lda, ldb, ldc): (c_int(768), c_int(131072), c_int(768)); (m, n, k): (c_int(24), c_int(4096), c_int(4096))
Traceback (most recent call last):
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/gradio/routes.py", line 384, in run_predict
output = await app.get_blocks().process_api(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/gradio/blocks.py", line 1020, in process_api
result = await self.call_function(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/gradio/blocks.py", line 844, in call_function
prediction = await anyio.to_thread.run_sync(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/home/touhi/Desktop/llm/Alpaca-LoRA-Serve/app.py", line 58, in chat_batch
bot_responses = get_output_batch(
File "/home/touhi/Desktop/llm/Alpaca-LoRA-Serve/gen.py", line 22, in get_output_batch
generated_id = model.generate(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/peft/peft_model.py", line 581, in generate
outputs = self.base_model.generate(**kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/generation/utils.py", line 1405, in generate
return self.greedy_search(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/generation/utils.py", line 2200, in greedy_search
outputs = self(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 765, in forward
outputs = self.model(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 614, in forward
layer_outputs = decoder_layer(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 309, in forward
hidden_states, self_attn_weights, present_key_value = self.self_attn(
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/transformers/models/llama/modeling_llama.py", line 209, in forward
query_states = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/accelerate/hooks.py", line 165, in new_forward
output = old_forward(*args, **kwargs)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/peft/tuners/lora.py", line 522, in forward
result = super().forward(x)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/bitsandbytes/nn/modules.py", line 242, in forward
out = bnb.matmul(x, self.weight, bias=self.bias, state=self.state)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/bitsandbytes/autograd/_functions.py", line 488, in matmul
return MatMul8bitLt.apply(A, B, out, bias, state)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/torch/autograd/function.py", line 506, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/bitsandbytes/autograd/_functions.py", line 377, in forward
out32, Sout32 = F.igemmlt(C32A, state.CxB, SA, state.SB)
File "/home/touhi/anaconda3/envs/alpaca/lib/python3.9/site-packages/bitsandbytes/functional.py", line 1410, in igemmlt
raise Exception('cublasLt ran into an error!')
Exception: cublasLt ran into an error!
error detected