properly skip float8 inference tests without fbgemm

[vkuzo]

Summary:

Makes the float8 inference tests pass if fbgemm_gpu_genai is not
installed, nice for local development.

Test Plan:

pytest test/quantization/quantize_/workflows/float8/test_float8_tensor.py -s -x

Reviewers:

Subscribers:

Tasks:

Tags:

[vkuzo]

Stack from ghstack (oldest at bottom):

• add bias handling for a_1_128_w_128_128 float8 scaling #3259
• add a_1_128_w_128_128 (DeepSeek) float8 scaling for inference #3257
• move float8 blockwise kernels out of prototype #3256
• -> properly skip float8 inference tests without fbgemm #3255

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3255

• 📄 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:

• Long queue for ROCM runners, also B200 and XPU queueing is observed

✅ No Failures

As of commit 990ef89 with merge base 3577306 ():
💚 Looks good so far! There are no failures yet. 💚

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