Raise a8wxdq load errors only when quant scheme is used

[Jack-Khuu]

As titled, originally the message was shown regardless of whether the scheme was used; tested on Mac (ARM)

---

Not Using Quant

> python3 torchchat.py generate llama3.1 --device cpu
Using device=cpu Apple M1 Max
Loading model...
Time to load model: 2.24 seconds
-----------------------------------------------------------

---

Using Quant

> OMP_NUM_THREADS=6 python3 torchchat.py generate llama3.1 --device cpu --dtype float32 --quantize '{"linear:a8wxdq": {"bitwidth": 4, "groupsize": 256, "has_weight_zeros": false}}'

w/o Loading

Using device=cpu Apple M1 Max
Loading model...
Time to load model: 2.74 seconds
Quantizing the model with: {'linear:a8wxdq': {'bitwidth': 4, 'groupsize': 256, 'has_weight_zeros': False}}
Time to quantize model: 0.00 seconds
Traceback (most recent call last):
  File "/Users/jackkhuu/Desktop/oss/torchchat/torchchat.py", line 83, in <module>
    generate_main(args)
  File "/Users/jackkhuu/Desktop/oss/torchchat/torchchat/generate.py", line 1093, in main
    gen = Generator(
          ^^^^^^^^^^
  File "/Users/jackkhuu/Desktop/oss/torchchat/torchchat/generate.py", line 284, in __init__
    self.model = _initialize_model(self.builder_args, self.quantize, self.tokenizer)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/jackkhuu/Desktop/oss/torchchat/torchchat/cli/builder.py", line 568, in _initialize_model
    quantize_model(
  File "/Users/jackkhuu/Desktop/oss/torchchat/torchchat/utils/quantize.py", line 84, in quantize_model
    raise Exception(f"Note: Failed to load torchao experimental a8wxdq quantizer with error: {a8wxdq_load_error}")
Exception: Note: Failed to load torchao experimental a8wxdq quantizer with error: [Errno 2] No such file or directory: '/Users/jackkhuu/Desktop/oss/torchchat/torchao-build/src/ao/torchao/experimental/quant_api.py'

w/ Loading

Using device=cpu Apple M1 Max
Loading model...
Time to load model: 2.98 seconds
Quantizing the model with: {'linear:a8wxdq': {'bitwidth': 4, 'groupsize': 256, 'has_weight_zeros': False}}

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1231

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• PyTorch Testing Nodes Undergoing ROCm 6.2.1 Upgrades

✅ No Failures

As of commit 6e1cdd5 with merge base 8278aa2 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.