Skip to content

Issues: pytorch/ao

[RFC] torchao Contributor Guide
#391 opened Jun 18, 2024 by jerryzh168
Open 16
float8 upcoming feature tracker
#556 opened Jul 30, 2024 by vkuzo
Open
Multibackend tracker
#1082 opened Oct 15, 2024 by msaroufim
Open
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

192 Open 149 Closed
192 Open 149 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Does torchao supoort VLM quantization and dequantization？
#1464 opened Dec 30, 2024 by yangd85
2
The internal torchao tensor subclasses cause errors with torch.compile
#1463 opened Dec 28, 2024 by JohnnyRacer
2
fuse ConvTranspose2d+BatchNorm2d+ReLU
#1462 opened Dec 28, 2024 by yokosyun
1
Linear Model not saved time using to_sparse_semi_structured triaged
#1460 opened Dec 26, 2024 by phyllispeng123
@jcaip
2
torchao/experimental/ CMAKE_SYSTEM_PROCESSOR checks need to accept aarch64 build triaged
#1457 opened Dec 22, 2024 by swolchok
@swolchok
QOL: easy way to run lint locally that matches the behavior in CI
#1448 opened Dec 19, 2024 by vkuzo
5
Segmentation Fault Running Int8 Quantized Model on GPU question Further information is requested triaged
#1437 opened Dec 18, 2024 by wendywangwwt
1
QLoRA Worse Memory When linear_nf4 Used on Output performance
#1433 opened Dec 18, 2024 by pbontrager
1
Bug: TypeError in SAM2ImagePredictor.predict() method bug Something isn't working triaged
#1431 opened Dec 18, 2024 by dongxiaolong
@cpuhrsch
3
Torchtune QAT + compile raises error
#1427 opened Dec 17, 2024 by felipemello1
@andrewor14
3
2:4 Sparse training sparsity
#1425 opened Dec 17, 2024 by phyllispeng123
@jcaip
4
Comparison of Quantization Error for Each Linear Operator ?
#1424 opened Dec 17, 2024 by Lenan22
1
Not saved time using WeightNormSparsifier sparsity
#1420 opened Dec 16, 2024 by phyllispeng123
@jcaip
2
FLoat8 Autocast Issue float8
#1418 opened Dec 16, 2024 by asahni04
1
Does Torch.ao Support FullyShardedDataParallel?
#1413 opened Dec 13, 2024 by Lenan22
4
[Feature Request] W4A4 Quantization Support in torchao topic: new feature Use this tag if this PR adds a new feature topic: performance Use this tag if this PR improves the performance of a feature
#1406 opened Dec 12, 2024 by xxw11
5
Does Torch Support NPU Architectures like Ascend MDC910B and Multi-GPU Quantization for Large Models? multibackend
#1405 opened Dec 12, 2024 by Lenan22
4
"Where is the overloaded function for torch.nn.functional.linear(aqt, original_weight_tensor, bias)? "
#1397 opened Dec 10, 2024 by Lenan22
2
[Feature Request] add universal GEMM kernels for ARM CPU to torchao/experimental
#1394 opened Dec 10, 2024 by metascroy
1
AO and Automated Mixed Precision question Further information is requested topic: documentation Use this tag if this PR adds or improves documentation
#1390 opened Dec 8, 2024 by bhack
@jerryzh168
13
EfficientTAM topic: new feature Use this tag if this PR adds a new feature topic: performance Use this tag if this PR improves the performance of a feature
#1384 opened Dec 5, 2024 by bhack
7
unhashable type: non-nested SymInt autoquant bug Something isn't working
#1381 opened Dec 4, 2024 by bhack
@jerryzh168
32
[Feature Request] Add dynamic kernel selection to torchao/experimental
#1376 opened Dec 4, 2024 by metascroy
@Darshcg
5
Can't use AdamW? optimizer
#1363 opened Dec 2, 2024 by waka45
1
Use unittest instead of pytest everywhere
#1321 opened Nov 21, 2024 by jerryzh168
ProTip! Exclude everything labeled bug with -label:bug.