Minor fixes to PT2 export path: enum typo and max_seq_len

[Jack-Khuu]

2 mini fixes on #896

• Enum logic typos (was not found when testing originally due to Python magic)
• max_seq_len discrepancy (found when testing)

python3 torchchat.py export llama3.1 --quantize '{"precision": {"dtype":"bfloat16"}, "executor":{"accelerator":"cuda"}}' --output-aoti-package-path /tmp/model3.pt2

python3 torchchat.py generate llama3.1 --aoti-package-path /tmp/model3.pt2 --prompt "Once upon a time,"  --num-samples 3

Compared to

python3 torchchat.py export llama3.1 --quantize '{"precision": {"dtype":"bfloat16"}, "executor":{"accelerator":"cuda"}}' --output-dso-path /tmp/model3.so

python3 torchchat.py generate llama3.1 --dso-path /tmp/model3.so --prompt "Once upon a time,"  --num-samples 3

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1343

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit f35d5fc with merge base 4510ba0 ():
💚 Looks good so far! There are no failures yet. 💚

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