Make SmoothQuant more General #2728

namgyu-youn · 2025-08-11T04:52:51Z

Summary

Add SmoothQuantConfig as a base config and SmoothQuantObserver as a smoothing factor computation. Apply corresponding changes in other parts for the SmoothQuant API flows.

Benchmark

All experiments use the meta-llama/Llama-2-7b-chat-hf model with max sequence length (SeqLen) 512 and calibration limit 128 on a 1xH100 80GB HBM2 instance. For comprehensive benchmarking, we compare three cases: 1. origin, 2. W8A8, 3. SmoothQuant (W8A8). Result shows SmoothQuant with W8A8 slightly increase perplexity, reducing latency 33.82%. Since tinygemm kernel only uses bfloat16 inputs, Tokens/sec decreases for float16 input.

Precision dtype	Quantization	Perplexity	Tokens/sec	PPL Change	Speed Change
bfloat16	-	6.93	667	-	-
bfloat16*	-	6.93	27 🐌	-	-
bfloat16	W8A8-dynamic	7.35	1,967	+6.07%	+33.89%
bfloat16	W8A8-dynamic**	7.03	1,972	+1.39%	+33.82%
float16	-	6.93	625	-	-
float16	W8A8-dynamic	7.29	523	+5.21%	-19.42%
float16	W8A8-dynamic**	6.94	516	+0.21%	-21.23%
bfloat16*	W8A8-dynamic**	6.92	3 🐌	-0.18%	-768.29%

*Used with torch.compile, **Used with SmoothQuant

Test Plan

This PR addresses the prototype benchmark. Experiments are recorded in the "Benchmark" section using example.py with Llama-2-7b-chat-hf for both quantization and model saving. Unittest is also updated for the change.

Future Plan

Build a benchmark within the vLLM ecosystem for AWQ and SmoothQuant. See #2815 for more info

Summary: - Added SmoothQuantConfig as a base config and made corresponding changes in other parts of the flow Test Plan: - Qwen 3-8B with example.py and unittest - Additional test plans requirerd ETC - Fix typo in README.md for SmoothQuant

pytorch-bot · 2025-08-11T04:52:55Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2728

📄 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 bd6bf13 with merge base 2eae09b ():
💚 Looks good so far! There are no failures yet. 💚

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

namgyu-youn · 2025-08-15T17:44:09Z

@jerryzh168 Could you please look into this PR? It was inspired by #2659 (comment) for more generalized SmoothQuant API.

jerryzh168 · 2025-08-15T17:49:18Z

Thanks @namgyu-youn this is a step towards that but not fully general yet, it seems to be a quick change to add it though, commented inline.

also it seems smoothquant is not very popular at the moment: https://huggingface.co/models?search=smoothquant, so I'd like to wait a bit before we invest more effort to it, let me know if you are interested to contribute more to torchao, we have many more higher priority issues that you can help with I think

test/prototype/test_smoothquant.py

torchao/prototype/smoothquant/api.py

namgyu-youn · 2025-08-15T18:57:29Z

Thanks @namgyu-youn this is a step towards that but not fully general yet, it seems to be a quick change to add it though, commented inline.

also it seems smoothquant is not very popular at the moment: https://huggingface.co/models?search=smoothquant, so I'd like to wait a bit before we invest more effort to it, let me know if you are interested to contribute more to torchao, we have many more higher priority issues that you can help with I think

Thanks for the kind info, and I truly love your team's work after reviewing TorchAO: CodeML @ ICML 2025.

The recently updated contribution guide could be a great choice for the next contribution, but personally I prefer the sparsity (pruning) module more. Unfortunately, I heard the main POC (@jcaip) is on vacation, making it hard for me to progress. The following are my recent activities related to the sparsity module:

Since Wanda was already introduced, I recently introduced Wanda++ at feat: RGS for wanda++ #2537.
Computation overhead was missing in your team's workshop (not certain because of my lack of knowledge), and opened issue at Missing benchmark for sparse24_sm90_sparsify overhead #2612
Also interested in Activation compression Accelerate activation sparsity with activation compression #1920, but I have to learn more about it.

If there is no huge progress for the sparsity module, quantization (new APIs or primitive ops) might be a next step. Let me know if there is a good-second-issue about it.

p.s. Could you please check #2644 ? It hasn't merged yet after being approved (no CI broken). Also, #2660 has been waiting for review (I am fine to close this because it is low-priority).

namgyu-youn · 2025-08-16T18:35:40Z

Test result (test_smoothquant.py):

$ python test/prototype/test_smoothquant.py
..............................................
----------------------------------------------------------------------
Ran 46 tests in 15.208s

OK

namgyu-youn · 2025-08-16T18:35:58Z

@jerryzh168 Hi, I am happy to show you more generalized SmoothQuant API by using Quantization API (torchao/quantization/quant_api.py) at ba89d03. Could you review this PR?

test/prototype/test_smoothquant.py

torchao/prototype/smoothquant/README.md

jerryzh168 · 2025-08-18T22:52:29Z

torchao/prototype/smoothquant/example.py

-        insert_smooth_quant_observer_(model, alpha, quant_mode)
+        # Step 1: Insert observers to find average magnitude and calculate scales
+        config = SmoothQuantConfig(
+            base_config=int8_dynamic_activation_int8_weight(),


can generalize the example API to take quant type configs now, see

ao/torchao/prototype/awq/example.py

Line 307 in 751d7f6

help="Quantization method. Options are either awq-int4wo-<group_size>, or int4wo-<group_size>.",

Thanks, but how about using Int8DynamicActivationInt8WeightConfig as a default in here and devide PR? It might require checking which APIs are compatiable with SmoothQuantConfig, and building unittest.

~~btw, we can uniform commonly used utils functions in AWQ and SmoothQuant: get_calib_dataset, wiki2_eval, and quantize_and_eval.~~

torchao/prototype/smoothquant/api.py

torchao/prototype/smoothquant/core.py

jerryzh168 · 2025-08-19T18:08:14Z

torchao/prototype/smoothquant/example.py

+    print(f"time for convert: {time.time() - t0:.02f} seconds")
+
+    # Set up config for loading
+    quant_config.step = SmoothQuantStep.PREPARE_FOR_LOADING


does this work? you can check if it works by the following:

export MODEL=YOUR_SAVED_SMOOTHQUANT_MODEL lm_eval --model hf --model_args pretrained=$MODEL --tasks $TASK --device cuda:0 --batch_size auto --limit 50 # vllm export MODEL=YOUR_SAVED_SMOOTHQUANT_MODEL python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model $MODEL

Hoped so because it works similarly to AWQ, but just tested it with the following code for assurance and got the log message:

import tempfile import torch from transformers import AutoModelForCausalLM, AutoTokenizer from torchao.prototype.smoothquant import SmoothQuantConfig from torchao.prototype.smoothquant.core import SmoothQuantStep from torchao.prototype.smoothquant.example import quantize_and_eval from torchao.quantization import quantize_ from torchao.quantization.quant_api import Int8DynamicActivationInt8WeightConfig MODEL_NAME = "microsoft/DialoGPT-small" # Step 1: Create quantized model with tempfile.NamedTemporaryFile(suffix='.pt', delete=False) as f: model_path = f.name quantize_and_eval(MODEL_NAME, 0.5, ['PPL'], 256, 5, 'cuda', torch.float32, False, model_path, None) # Step 2: Test PREPARE_FOR_LOADING tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) tokenizer.pad_token = tokenizer.eos_token model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float32).cuda() quantize_(model, SmoothQuantConfig( base_config=Int8DynamicActivationInt8WeightConfig(), step=SmoothQuantStep.PREPARE_FOR_LOADING, alpha=0.5, )) # Test inference test_input = tokenizer('Hello world', return_tensors='pt').to('cuda') with torch.no_grad(): output = model(**test_input) generated = model.generate(**test_input, max_length=20, do_sample=False) print(f"✓ Inference: {output.logits.shape}") print(f"✓ Generation: {tokenizer.decode(generated[0], skip_special_tokens=True)}")

Loading model on cuda... Time to load model: 1.86 seconds running SmoothQuant prepare and calibrate Repo card metadata block was not found. Setting CardData to empty. Token indices sequence length is longer than the specified maximum sequence length for this model (1443 > 1024). Running this sequence through the model will result in indexing errors time for prepare and calibration: 5.20 seconds running SmoothQuant convert time for convert: 0.04 seconds Saving model to /tmp/tmpqeme5s1r.pt `loss_type=None` was set in the config but it is unrecognised.Using the default loss: `ForCausalLMLoss`. Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation. ✓ Inference: torch.Size([1, 4, 50257]) ✓ Generation: TorchAO TorchAO

For sure, we should benchmark them with your suggestion, but I want to carefully suggest dividing its PR.

OK sounds good to divide the PR

jerryzh168

please add a test for sanity checking the accuracy / functionality of smoothquant implementation, see comments inline

jerryzh168

Thanks! looks good

jerryzh168 · 2025-09-05T19:33:56Z

the error seems to be real: https://github.com/pytorch/ao/actions/runs/17455759907/job/49707357714?pr=2728 you can't import from test files, can you define the ToyLinearModel in test_smoothquant itself?

test/integration/test_integration.py

jerryzh168

please revert changes to test_integration.py

also can you run the tests locally first?

namgyu-youn · 2025-09-07T16:56:02Z

also can you run the tests locally first?

Unfortunately, I am unavailable to L40s. Here is the locally tested result in A100 80GB PCIe MIG instance.

Result of integration test after revert

$ pytest test/integration --verbose -s
===================================================================================================== warnings summary =====================================================================================================
.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97
.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97
  /home/elicer/ao/.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97: DeprecationWarning: warmup, rep, and use_cuda_graph parameters are deprecated. See https://github.com/triton-lang/triton/pull/4496 for details.
    warnings.warn(("warmup, rep, and use_cuda_graph parameters are deprecated. See "

torchao/utils.py:408
  /home/elicer/ao/torchao/utils.py:408: UserWarning: TORCH_VERSION_AT_LEAST_2_8 is deprecated and will be removed in torchao 0.14.0
    warnings.warn(self.msg)

test/integration/test_integration.py::TestSubclass::test_int8_weight_only_quant_subclass_3_cuda
  /home/elicer/ao/.venv/lib/python3.10/site-packages/torch/_inductor/compile_fx.py:282: UserWarning: TensorFloat32 tensor cores for float32 matrix multiplication available but not enabled. Consider setting `torch.set_float32_matmul_precision('high')` for better performance.
    warnings.warn(

test/integration/test_integration.py: 49 warnings
  /home/elicer/ao/torchao/utils.py:408: UserWarning: TORCH_VERSION_AT_LEAST_2_7 is deprecated and will be removed in torchao 0.14.0
    warnings.warn(self.msg)

test/integration/test_integration.py::SmoothquantIntegrationTest::test_on_dummy_distilbert
  /home/elicer/ao/test/integration/test_integration.py:1429: DeprecationWarning: torch.ao.quantization is deprecated and will be removed in 2.10. 
  For migrations of users: 
  1. Eager mode quantization (torch.ao.quantization.quantize, torch.ao.quantization.quantize_dynamic), please migrate to use torchao eager mode quantize_ API instead 
  2. FX graph mode quantization (torch.ao.quantization.quantize_fx.prepare_fx,torch.ao.quantization.quantize_fx.convert_fx, please migrate to use torchao pt2e quantization API instead (prepare_pt2e, convert_pt2e) 
  3. pt2e quantization has been migrated to torchao (https://github.com/pytorch/ao/tree/main/torchao/quantization/pt2e) 
  see https://github.com/pytorch/ao/issues/2259 for more details
    model_copy2 = torch.ao.quantization.quantize_dynamic(

test/integration/test_integration.py::SmoothquantIntegrationTest::test_on_dummy_distilbert
  /home/elicer/ao/.venv/lib/python3.10/site-packages/torch/ao/quantization/quantize.py:566: DeprecationWarning: torch.ao.quantization is deprecated and will be removed in 2.10. 
  For migrations of users: 
  1. Eager mode quantization (torch.ao.quantization.quantize, torch.ao.quantization.quantize_dynamic), please migrate to use torchao eager mode quantize_ API instead 
  2. FX graph mode quantization (torch.ao.quantization.quantize_fx.prepare_fx,torch.ao.quantization.quantize_fx.convert_fx, please migrate to use torchao pt2e quantization API instead (prepare_pt2e, convert_pt2e) 
  3. pt2e quantization has been migrated to torchao (https://github.com/pytorch/ao/tree/main/torchao/quantization/pt2e) 
  see https://github.com/pytorch/ao/issues/2259 for more details
    convert(model, mapping, inplace=True)

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
================================================================================ 152 passed, 207 skipped, 55 warnings in 124.51s (0:02:04) =================================================================================

Result of SmoothQuant test

$ pytest test/prototype/test_smoothquant.py --verbose -s
=================================================================================================== test session starts ====================================================================================================
platform linux -- Python 3.10.15, pytest-8.4.2, pluggy-1.6.0 -- /home/elicer/ao/.venv/bin/python3
cachedir: .pytest_cache
hypothesis profile 'default'
rootdir: /home/elicer/ao
plugins: hypothesis-6.138.14
collecting ... TMA benchmarks will be running without grid constant TMA descriptor.
collected 6 items                                                                                                                                                                                                          

test/prototype/test_smoothquant.py::TestSmoothQuant::test_observer_insertion_base_config0 PASSED
test/prototype/test_smoothquant.py::TestSmoothQuant::test_prepare_for_loading_base_config0 PASSED
test/prototype/test_smoothquant.py::TestSmoothQuant::test_smoothquant_accuracy_alpha_0_5_base_config0_device_cpu_bfloat16 convert: module is not SmoothQuantObservedLinear, skipping: <class 'torch.nn.modules.linear.Linear
'>                                                                                                                                                                                                                          PASSED
test/prototype/test_smoothquant.py::TestSmoothQuant::test_smoothquant_accuracy_alpha_0_5_base_config0_device_cuda_bfloat16 convert: module is not SmoothQuantObservedLinear, skipping: <class 'torch.nn.modules.linear.Linea
r'>                                                                                                                                                                                                                         PASSED
test/prototype/test_smoothquant.py::TestSmoothQuant::test_smoothquant_accuracy_alpha_0_75_base_config0_device_cpu_bfloat16 convert: module is not SmoothQuantObservedLinear, skipping: <class 'torch.nn.modules.linear.Linea
r'>                                                                                                                                                                                                                         PASSED
test/prototype/test_smoothquant.py::TestSmoothQuant::test_smoothquant_accuracy_alpha_0_75_base_config0_device_cuda_bfloat16 convert: module is not SmoothQuantObservedLinear, skipping: <class 'torch.nn.modules.linear.Line
ar'>                                                                                                                                                                                                                        PASSED

===================================================================================================== warnings summary =====================================================================================================
.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97
.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97
  /home/elicer/ao/.venv/lib/python3.10/site-packages/triton/runtime/autotuner.py:97: DeprecationWarning: warmup, rep, and use_cuda_graph parameters are deprecated. See https://github.com/triton-lang/triton/pull/4496 for 
details.                                                                                                                                                                                                                        warnings.warn(("warmup, rep, and use_cuda_graph parameters are deprecated. See "

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
============================================================================================== 6 passed, 2 warnings in 4.98s ===============================================================================================

jerryzh168 · 2025-09-10T03:26:03Z

please skip the failed test when there is no cuda like this:

ao/test/quantization/quantize_/workflows/int4/test_int4_tensor.py

Line 28 in d35c2ce

@unittest.skipIf(not torch.cuda.is_available(), "Need CUDA available")

namgyu-youn · 2025-09-10T16:50:17Z

please skip the failed test when there is no cuda like this:

ao/test/quantization/quantize_/workflows/int4/test_int4_tensor.py

Line 28 in d35c2ce

@unittest.skipIf(not torch.cuda.is_available(), "Need CUDA available")

Done, could you look into it?

Xia-Weiwen · 2025-09-28T01:15:05Z

This PR is titled "Make SmoothQuant more General" however it removes static quant support and prevents UT running in CPU-only environments, which actually makes SmoothQuant more specific.

namgyu-youn · 2025-09-28T11:13:25Z

This PR is titled "Make SmoothQuant more General" however it removes static quant support and prevents UT running in CPU-only environments, which actually makes SmoothQuant more specific.

@Xia-Weiwen We decided to split the PR to support more quantization APIs, as discussed in #2728 (comment). In fact, what "general" refers to here is the new SmoothQuant API structure (config -> quantize (convert)). Please check the following unit test and reproduce it for more quantization APIs:

ao/test/prototype/test_smoothquant.py

Lines 127 to 164 in 0d3217d

    
               @common_utils.parametrize( 
        
                   "base_config", 
        
                   [ 
        
                       Int8DynamicActivationInt8WeightConfig(), 
        
                       # TODO: Check more quantization APIs 
        
                   ], 
        
               ) 
        
               def test_observer_insertion(self, base_config): 
        
                   """Test that PREPARE step correctly inserts SmoothQuantObservedLinear.""" 
        
                   m = ToyLinearModel().eval() 
        
                   # Before quantization - should be regular Linear 
        
                   self.assertIsInstance(m.linear1, torch.nn.Linear) 
        
                   self.assertNotIsInstance(m.linear1, SmoothQuantObservedLinear) 
        
                   # PREPARE step - should insert observers 
        
                   config = SmoothQuantConfig( 
        
                       base_config=base_config, 
        
                       step=SmoothQuantStep.PREPARE, 
        
                   ) 
        
                   quantize_(m, config) 
        
                   # After PREPARE - should be SmoothQuantObservedLinear 
        
                   self.assertIsInstance(m.linear1, SmoothQuantObservedLinear) 
        
                   self.assertTrue(hasattr(m.linear1, "obs")) 
        
                   # Test calibration 
        
                   test_data = torch.randn(2, 512) 
        
                   m(test_data) 
        
                   # CONVERT step - should produce regular Linear with quantized weights 
        
                   config.step = SmoothQuantStep.CONVERT 
        
                   quantize_(m, config) 
        
                   # After CONVERT - should be regular Linear again (but quantized) 
        
                   self.assertIsInstance(m.linear1, torch.nn.Linear) 
        
                   self.assertNotIsInstance(m.linear1, SmoothQuantObservedLinear)

Make SmoothQuant more General

c482371

Summary: - Added SmoothQuantConfig as a base config and made corresponding changes in other parts of the flow Test Plan: - Qwen 3-8B with example.py and unittest - Additional test plans requirerd ETC - Fix typo in README.md for SmoothQuant

meta-cla 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 Aug 11, 2025

refactor: use predefined ToyLinearModel

e16edc2

namgyu-youn marked this pull request as draft August 12, 2025 06:53

namgyu-youn added 2 commits August 12, 2025 16:51

fix incorrect parameters

5ec0dcf

add type hint for dataclass

2475ad1

namgyu-youn marked this pull request as ready for review August 12, 2025 08:01

Merge branch 'main' into refactor-smoothquant

ccb7b84

jerryzh168 approved these changes Aug 15, 2025

View reviewed changes

jerryzh168 reviewed Aug 15, 2025

View reviewed changes

test/prototype/test_smoothquant.py Outdated Show resolved Hide resolved

jerryzh168 reviewed Aug 15, 2025

View reviewed changes

torchao/prototype/smoothquant/api.py Outdated Show resolved Hide resolved

jerryzh168 self-requested a review August 15, 2025 17:53

namgyu-youn marked this pull request as draft August 16, 2025 15:27

use Quantization API for more generalized SmoothQuant API

ba89d03

namgyu-youn marked this pull request as ready for review August 16, 2025 18:31

jerryzh168 reviewed Aug 18, 2025

View reviewed changes

test/prototype/test_smoothquant.py Outdated Show resolved Hide resolved

jerryzh168 reviewed Aug 18, 2025

View reviewed changes

torchao/prototype/smoothquant/README.md Outdated Show resolved Hide resolved

jerryzh168 reviewed Aug 18, 2025

View reviewed changes

torchao/prototype/smoothquant/api.py Show resolved Hide resolved

namgyu-youn added 2 commits August 19, 2025 18:54

add PREPARE_FOR_LOADING mode for loading quantized weight

a6df6af

update example and doc for updated SmoothQuant API

0fc6539

namgyu-youn requested a review from jerryzh168 August 19, 2025 11:03

jerryzh168 reviewed Aug 19, 2025

View reviewed changes

torchao/prototype/smoothquant/core.py Outdated Show resolved Hide resolved

jerryzh168 reviewed Aug 19, 2025

View reviewed changes

namgyu-youn requested a review from jerryzh168 September 3, 2025 14:39

update integration test for new SmoothQuant API

50dedb8

jerryzh168 requested changes Sep 3, 2025

View reviewed changes

add unittest: sanity check for smoothquant acc

bb25adb

namgyu-youn requested a review from jerryzh168 September 4, 2025 06:49

jerryzh168 approved these changes Sep 5, 2025

View reviewed changes

bugfix: ImportError for ToyLinearModel

e630948

namgyu-youn requested a review from jerryzh168 September 6, 2025 04:19

jerryzh168 reviewed Sep 7, 2025

View reviewed changes

test/integration/test_integration.py Show resolved Hide resolved

jerryzh168 requested changes Sep 7, 2025

View reviewed changes

revert: smoothquant unit test name

4eca4c2

namgyu-youn added 3 commits September 8, 2025 01:56

revert: integration test

759f86f

update docs

844a8af

update docs

f756df9

namgyu-youn requested a review from jerryzh168 September 7, 2025 17:29

jerryzh168 added the topic: improvement Use this tag if this PR is an improvement (doesn't fit into any of the other categories) label Sep 9, 2025

add skiptest: no cuda case

bd6bf13

jerryzh168 approved these changes Sep 11, 2025

View reviewed changes

jerryzh168 merged commit cc35151 into pytorch:main Sep 11, 2025
18 checks passed

namgyu-youn deleted the refactor-smoothquant branch September 11, 2025 05:11

namgyu-youn mentioned this pull request Sep 18, 2025

Update SmoothQuant to use subtensor instead of external wrapper #3012

Closed

This was referenced Sep 30, 2025

Improve SmoothQuant test cases #3101

Merged

make smoothquant more PT2 friendly #1639

Open

namgyu-youn mentioned this pull request Oct 14, 2025

Static quant support for SmoothQuant #3089

Closed

Make SmoothQuant more General #2728

Make SmoothQuant more General #2728

Conversation

namgyu-youn commented Aug 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Benchmark

Test Plan

Future Plan

Uh oh!

pytorch-bot bot commented Aug 11, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2728

✅ No Failures

Uh oh!

namgyu-youn commented Aug 15, 2025

Uh oh!

jerryzh168 commented Aug 15, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Uh oh!

namgyu-youn commented Aug 15, 2025

Uh oh!

namgyu-youn commented Aug 16, 2025

Uh oh!

namgyu-youn commented Aug 16, 2025

Uh oh!

Uh oh!

Uh oh!

jerryzh168 Aug 18, 2025

Choose a reason for hiding this comment

Uh oh!

namgyu-youn Aug 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jerryzh168 Aug 19, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

jerryzh168 Aug 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

namgyu-youn Aug 19, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

jerryzh168 Aug 20, 2025

Choose a reason for hiding this comment

Uh oh!

jerryzh168 left a comment

Choose a reason for hiding this comment

Uh oh!

jerryzh168 left a comment

Choose a reason for hiding this comment

Uh oh!

jerryzh168 commented Sep 5, 2025

Uh oh!

Uh oh!

jerryzh168 left a comment

Choose a reason for hiding this comment

Uh oh!

namgyu-youn commented Sep 7, 2025

Uh oh!

jerryzh168 commented Sep 10, 2025

Uh oh!

namgyu-youn commented Sep 10, 2025

Uh oh!

Uh oh!

Xia-Weiwen commented Sep 28, 2025

Uh oh!

namgyu-youn commented Sep 28, 2025

Uh oh!

Reviewers

Assignees

Labels

namgyu-youn commented Aug 11, 2025 •

edited

Loading

pytorch-bot bot commented Aug 11, 2025 •

edited

Loading

jerryzh168 commented Aug 15, 2025 •

edited

Loading

namgyu-youn Aug 19, 2025 •

edited

Loading

jerryzh168 Aug 19, 2025 •

edited

Loading

namgyu-youn Aug 19, 2025 •

edited

Loading