Skip to content

Move QAT out of prototype#1091

Merged
facebook-github-bot merged 4 commits into
gh/andrewor14/8/basefrom
gh/andrewor14/8/head
Oct 22, 2024
Merged

Move QAT out of prototype#1091
facebook-github-bot merged 4 commits into
gh/andrewor14/8/basefrom
gh/andrewor14/8/head

Conversation

@andrewor14

@andrewor14 andrewor14 commented Oct 16, 2024 •
edited
Loading

Copy link
Copy Markdown
Contributor

Stack from ghstack (oldest at bottom):

Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

BC-breaking notes

Before:

from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)

After:

from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)

Test Plan:
python test/quantization/test_qat.py

Differential Revision: D64555609

@andrewor14
Move QAT out of prototype
a5a0428 
Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

[ghstack-poisoned]
@pytorch-bot

pytorch-bot Bot commented Oct 16, 2024 •
edited
Loading

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1091

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

✅ No Failures

As of commit fc9c1a9 with merge base 7aaf0ff (image):
💚 Looks good so far! There are no failures yet. 💚

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

andrewor14 added a commit that referenced this pull request Oct 16, 2024
@andrewor14
Move QAT out of prototype
05d4086 
Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: 9ebc45d
Pull Request resolved: #1091
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Oct 16, 2024
@andrewor14 andrewor14 mentioned this pull request Oct 16, 2024
Closed
@andrewor14 andrewor14 mentioned this pull request Oct 16, 2024
Closed
@andrewor14

andrewor14 commented Oct 16, 2024

Copy link
Copy Markdown
Contributor Author

(Don't merge this yet! Still need to ghimport once we figure out the diff train issue)

@andrewor14
Update on "Move QAT out of prototype"
58f402d 
**Summary:** Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

**Test Plan:**
python test/quantization/test_qat.py

[ghstack-poisoned]
andrewor14 added a commit that referenced this pull request Oct 17, 2024
@andrewor14
Move QAT out of prototype
35dbae7 
Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: cb72a8b
Pull Request resolved: #1091
@andrewor14

andrewor14 commented Oct 17, 2024

Copy link
Copy Markdown
Contributor Author

@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@andrewor14
Update on "Move QAT out of prototype"
b54f235 
**Summary:** Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

**Test Plan:**
python test/quantization/test_qat.py

Differential Revision: [D64555609](https://our.internmc.facebook.com/intern/diff/D64555609)

[ghstack-poisoned]
andrewor14 added a commit that referenced this pull request Oct 17, 2024
@andrewor14
Move QAT out of prototype
2187194 
Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**(Future) BC-breaking notes**

Note: This commit itself doesn't break BC yet. A future PR
will do that. The following is just to save this BC breaking
note somewhere.

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: 926354f
Pull Request resolved: #1091
@andrewor14
Update on "Move QAT out of prototype"
fc9c1a9 
**Summary:** Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**BC-breaking notes**

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

**Test Plan:**
python test/quantization/test_qat.py

Differential Revision: [D64555609](https://our.internmc.facebook.com/intern/diff/D64555609)

[ghstack-poisoned]
andrewor14 added a commit that referenced this pull request Oct 17, 2024
@andrewor14
Move QAT out of prototype
e2dd867 
Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**(Future) BC-breaking notes**

Note: This commit itself doesn't break BC yet. A future PR
will do that. The following is just to save this BC breaking
note somewhere.

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: add9dca
Pull Request resolved: #1091
@andrewor14

andrewor14 commented Oct 17, 2024

Copy link
Copy Markdown
Contributor Author

@andrewor14 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

@andrewor14 andrewor14 mentioned this pull request Oct 21, 2024
Closed
@facebook-github-bot facebook-github-bot merged commit dd4ad78 into gh/andrewor14/8/base Oct 22, 2024
andrewor14 added a commit to andrewor14/torchtune that referenced this pull request Oct 22, 2024
@andrewor14
Update imports after QAT was moved out of prototype
fc52849 
Summary: pytorch/ao#1091 moved QAT out of
prototype in torchao. This is a BC-breaking change so torchtune
also needs to update its QAT imports. Additionally, after
pytorch/ao#987 we decided that QAT in
torchao will use module swaps to insert fake quantizes, so there
is no need to have a separate module swap quantizer, so this
commit removes the `*ModuleSwapQuantizer` option.

Test Plan:
pytest -m integration_test tests/recipes/test_qat_distributed.py should work
@andrewor14 andrewor14 mentioned this pull request Oct 22, 2024
Merged
andrewor14 added a commit to andrewor14/torchtune that referenced this pull request Oct 22, 2024
@andrewor14
Update imports after QAT was moved out of prototype
d8f24c1 
Summary: pytorch/ao#1091 moved QAT out of
prototype in torchao. This is a BC-breaking change so torchtune
also needs to update its QAT imports. Additionally, after
pytorch/ao#987 we decided that QAT in
torchao will use module swaps to insert fake quantizes, so there
is no need to have a separate module swap quantizer, so this
commit removes the `*ModuleSwapQuantizer` option.

Test Plan:
pytest -m integration_test tests/recipes/test_qat_distributed.py should work
@andrewor14

andrewor14 commented Oct 23, 2024

Copy link
Copy Markdown
Contributor Author

Oh... this was merged into the wrong branch. I need to reopen this

@jerryzh168

jerryzh168 commented Oct 23, 2024

Copy link
Copy Markdown
Contributor

oh I see, that's why there is a fix up diff

@andrewor14

andrewor14 commented Oct 23, 2024

Copy link
Copy Markdown
Contributor Author

yeah exactly, opened #1152 to reland

andrewor14 added a commit that referenced this pull request Oct 24, 2024
@andrewor14
[reland] Move QAT out of prototype (#1152)
cf573bd 
Move QAT out of prototype

Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**(Future) BC-breaking notes**

Note: This commit itself doesn't break BC yet. A future PR
will do that. The following is just to save this BC breaking
note somewhere.

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: add9dca
Pull Request resolved: #1091
jainapurva pushed a commit that referenced this pull request Oct 24, 2024
@andrewor14 @jainapurva
[reland] Move QAT out of prototype (#1152)
1469c54 
Move QAT out of prototype

Summary: Move QAT out of prototype so we can provide stronger
BC guarantees moving forward.

**(Future) BC-breaking notes**

Note: This commit itself doesn't break BC yet. A future PR
will do that. The following is just to save this BC breaking
note somewhere.

Before:
```
from torchao.quantization.prototype.qat import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.prototype.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.prototype.qat.fake_quantizer import (
    FakeQuantizer,
)
```

After:
```
from torchao.quantization.qat import (
    ComposableQATQuantizer,
    Int4WeightOnlyQATQuantizer,
    Int4WeightOnlyEmbeddingQATQuantizer
    Int8DynActInt4WeightQATQuantizer,
)
from torchao.quantization.qat.linear import (
    disable_4w_fake_quant,
    disable_8da4w_fake_quant,
    enable_4w_fake_quant,
    enable_8da4w_fake_quant,
    Int8DynActInt4WeightQATLinear,
)
from torchao.quantization.qat.api import (
    FakeQuantizeConfig,
)
from torchao.quantization.qat.fake_quantizer import (
    FakeQuantizer,
)
```

Test Plan:
python test/quantization/test_qat.py

ghstack-source-id: add9dca
Pull Request resolved: #1091
andrewor14 added a commit to andrewor14/torchtune that referenced this pull request Oct 25, 2024
@andrewor14
Update imports after QAT was moved out of prototype
48dc978 
Summary: pytorch/ao#1091 moved QAT out of
prototype in torchao. This is a BC-breaking change so torchtune
also needs to update its QAT imports. Additionally, after
pytorch/ao#987 we decided that QAT in
torchao will use module swaps to insert fake quantizes, so there
is no need to have a separate module swap quantizer, so this
commit removes the `*ModuleSwapQuantizer` option.

Test Plan:
pytest -m integration_test tests/recipes/test_qat_distributed.py should work
andrewor14 added a commit to andrewor14/torchtune that referenced this pull request Oct 25, 2024
@andrewor14
Update imports after QAT was moved out of prototype
1d05e1a 
Summary: pytorch/ao#1091 moved QAT out of
prototype in torchao. This is a BC-breaking change so torchtune
also needs to update its QAT imports. Additionally, after
pytorch/ao#987 we decided that QAT in
torchao will use module swaps to insert fake quantizes, so there
is no need to have a separate module swap quantizer, so this
commit removes the `*ModuleSwapQuantizer` option.

Test Plan:
pytest -m integration_test tests/recipes/test_qat_distributed.py should work
yanbing-j pushed a commit to yanbing-j/ao that referenced this pull request Dec 9, 2024
@Jack-Khuu
[Hackability Refactor] File structure Re-organization under a torchch…
15066be 
…at/ folder (pytorch#1076)

* [Hackability Refactor] Move known_model_params under torchchat (pytorch#1073)

* [Hackability Refactor] Migrate CLI call sites to explicitly go through torchchat.py (pytorch#1075)

* [Hackability Refactor] Move model.py underneath torchchat/ (pytorch#1077)

* Move model.py

* Clear out init to avoid package circular import

* [Hackability Refactor] Move select top level docs into folders within torchchat (pytorch#1080)

* [Hackability Refactor] Move the top level util folder into torchchat/utils (pytorch#1079)

* [Hackability Refactor] Move the top level util file into torchchat/utils/

* Cleared out init to avoid packing

* [Hackability Refactor] Collapse gguf_util into gguf_loader (pytorch#1078)

* [Hackability Refactor] Collapse gguf_util into gguf_loader

* Update bad import

* [Hackability Refactor] Move model_config into torchchat/model_config (pytorch#1082)

* [Hackability Refactor] Move cli related files under torchchat/cli (pytorch#1083)

* [Hackability Refactor] Move build/util into torchchat/utils (pytorch#1084)

* [Hackability Refactor] Easy Moves: eval, gguf_loader, quantize, model_dist (pytorch#1085)

* [Hackability Refactor] Easy Cheap Moves: eval, gguf_loader, quantize, model_dist

* Update eval.py call sites that slipped through the initial pass

* [Hackability Refactor] Update missed direct file calls to use torchchat.py (pytorch#1088)

* [Hackability Refactor] Move export and generate under torchchat/ (pytorch#1089)

* [Hackability Refactor] Move scripts under torchchat/utils (pytorch#1090)

* [Hackability Refactor] Move scripts under torchchat/utils

* Fix install script for AOTI

* Update referenced path in build_android

* Adding missing utils path

* Add another layer for torchchat

* Move the source command depending on if TC root is defined

* [Hackability Refactor] Move installation related files into install/ (pytorch#1081)

* [Hackability Refactor] Move installation related files into install/

* Fix install req path

* Test fix with install path for bash

* Debug messages

* Remove changes to install in et_python_libs

* Remove debug echo

* Fix pin path for et

* [Hackability Refactor] Restricted Lint (pytorch#1091)

* [Hackability Refactor] Removing __main__ from export/generate/eval (pytorch#1092)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@jerryzh168 jerryzh168 jerryzh168 approved these changes

@jainapurva jainapurva jainapurva approved these changes

@vkuzo vkuzo Awaiting requested review from vkuzo

Assignees

No one assigned

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@andrewor14 @jerryzh168 @jainapurva @facebook-github-bot