can not open urls

[zzksdu]

run this command: python -m web_demo.server --model_path /mnt/local_path/demo_VITA_ckpt, and it print info as follows:

Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 0% Completed | 0/4 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:09<00:29, 9.71s/it]
Loading safetensors checkpoint shards: 25% Completed | 1/4 [00:10<00:30, 10.23s/it]
Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:22<00:22, 11.35s/it]
Loading safetensors checkpoint shards: 50% Completed | 2/4 [00:22<00:22, 11.27s/it]
Loading safetensors checkpoint shards: 75% Completed | 3/4 [00:47<00:17, 17.77s/it]
Loading safetensors checkpoint shards: 75% Completed | 3/4 [00:48<00:18, 18.13s/it]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [01:14<00:00, 21.39s/it]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [01:14<00:00, 18.73s/it]

[2025-03-26 17:34:14.578] Uninitialized parameters: ['model.audio_encoder.encoder.global_cmvn.istd', 'model.audio_encoder.encoder.global_cmvn.mean']
Loading safetensors checkpoint shards: 100% Completed | 4/4 [01:15<00:00, 21.77s/it]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [01:15<00:00, 18.88s/it]

[2025-03-26 17:34:15.188] Uninitialized parameters: ['model.audio_encoder.encoder.global_cmvn.istd', 'model.audio_encoder.encoder.global_cmvn.mean']
INFO 03-26 17:34:15 model_runner.py:890] Loading model weights took 15.5767 GB
INFO 03-26 17:34:15 model_runner.py:890] Loading model weights took 15.5767 GB
XGPU-lite: L-235:func: cuInit, pid: 15824, tid: 15824, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15823, tid: 15823, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15823, tid: 15823, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15824, tid: 15824, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15824, tid: 15824, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15823, tid: 15823, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15824, tid: 15824, flags: 0
XGPU-lite: L-235:func: cuInit, pid: 15823, tid: 15823, flags: 0
INFO 03-26 17:34:29 gpu_executor.py:121] # GPU blocks: 55016, # CPU blocks: 4681
INFO 03-26 17:34:30 gpu_executor.py:121] # GPU blocks: 55016, # CPU blocks: 4681
INFO 03-26 17:34:34 model_runner.py:1181] Capturing the model for CUDA graphs. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.
INFO 03-26 17:34:34 model_runner.py:1185] CUDA graphs can take additional 13 GiB memory per GPU. If you are running out of memory, consider decreasing gpu_memory_utilization or enforcing eager mode. You can also reduce the max_num_seqs as needed to decrease memory usage.
INFO 03-26 17:34:35 model_runner.py:1181] Capturing the model for CUDA graphs. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.
INFO 03-26 17:34:35 model_runner.py:1185] CUDA graphs can take additional 13 GiB memory per GPU. If you are running out of memory, consider decreasing gpu_memory_utilization or enforcing eager mode. You can also reduce the max_num_seqs as needed to decrease memory usage.
INFO 03-26 17:34:55 model_runner.py:1300] Graph capturing finished in 21 secs.
WARNING 03-26 17:34:55 sampling_params.py:221] temperature 0.001 is less than 0.01, which may cause numerical errors nan or inf in tensors. We have maxed it out to 0.01.
INFO 03-26 17:34:56 model_runner.py:1300] Graph capturing finished in 21 secs.
WARNING 03-26 17:34:56 sampling_params.py:221] temperature 0.001 is less than 0.01, which may cause numerical errors nan or inf in tensors. We have maxed it out to 0.01.
it seems no error, but i cant open this url: (https://127.0.0.1:8081)

so, can you give me some suggestions to solve this issue?
@lxysl @linhaojia13 @BradyFU @longzw1997

[lxysl]

Where do you deploy the backend, server or localhost? You can develop a simple Flask APP to test whether the network environment and route is correct.