chore(deps): Bump torchao from 0.11 to 0.13.0

[dependabot]

Bumps torchao from 0.11 to 0.13.0.

Release notes

Sourced from torchao's releases.

v0.13.0

Highlights

We are excited to announce the 0.13.0 release of torchao! This release adds support for numerous QAT improvements, faster mxfp8 pretraining and more!

Simpler Multi-step QAT API (pytorch/ao#2629)

We added a new, simpler, multi-step QAT API that uses only a single config. Now users can specify the target post-training quantization (PTQ) config as the base config and we will automatically infer the correct fake quantize configs to use!

from torchao.quantization import (
    quantize_,
    Int8DynamicActivationInt4WeightConfig
)
from torchao.quantization.qat import QATConfig
prepare
base_config = Int8DynamicActivationInt4WeightConfig(group_size=32)
qat_config = QATConfig(base_config, step="prepare")
quantize_(m, qat_config)
train (not shown)
convert
quantize_(m, QATConfig(base_config, step="convert"))

For more advanced use cases, users can continue to specify specific FakeQuantizeConfigs as before:

# prepare
activation_config = IntxFakeQuantizeConfig(torch.int8, "per_token", is_symmetric=False)
weight_config = IntxFakeQuantizeConfig(torch.int4, group_size=32)
qat_config = QATConfig(
    activation_config=activation_config,
    weight_config=weight_config,
    step="prepare",
)
quantize_(model, qat_config)
train and convert (not shown)

(Prototype) NVFP4 and FP8 QAT (pytorch/ao#2735, pytorch/ao#2666)

We generalized QAT to support FP8 and NVFP4 use cases. You can try them out as follows:

from torchao.quantization import (
    quantize_,
</tr></table> 

... (truncated)

Commits

• e318546 another fix for torch version (#2922)
• 1e487c2 change missing ops printout back to debug (#2921)
• adb8f1a fix torchao version check on torch version (#2918)
• 4dde983 torchao init: do not load .so files for known incompatible torch version (#2908)
• 13029fb Support QAT int4 v1 path for BC (#2888)
• 489c70e Update build_wheels_linux.yml
• f3e549c Add NVFP4 QAT (#2666)
• bc2c83e [reland] Refactor TorchAOBaseTensor for better BC (#2793) (#2855)
• 98e406d Add test for lut based embedding quantization.
• 7f7f626 Add lut quantized embedding.
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Superseded by #188.