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

174 Open 136 Closed
174 Open 136 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

Very large discrepancy in the quantized model's output compared to the original model when quantizing on CPU
#1335 opened Nov 23, 2024 by JohnnyRacer
4
Use unittest instead of pytest everywhere
#1321 opened Nov 21, 2024 by jerryzh168
[Feature Request] Support of int8_dynamic_activation_int8_weight with asymmetrically quantized weights
#1320 opened Nov 20, 2024 by sanchitintel
1 task
3
int8_dynamic_activation_int8_weight uses zero-points for weight when activation is asymmetrically quantized
#1317 opened Nov 20, 2024 by sanchitintel
2
How to trigger torchao unit tests?
#1315 opened Nov 19, 2024 by goldhuang
3
torch.compile(sync_float8_amax_and_scale_history) not working with triton latest main
#1311 opened Nov 19, 2024 by goldhuang
2
[AQT] Failed to move compiled module with AQT to a different device bug Something isn't working
#1309 opened Nov 19, 2024 by gau-nernst
2
[float8] DDP GPT1.5B Torch.compile dynamo error
#1308 opened Nov 19, 2024 by OrenLeung
1
pip install torchao cannot get latest versions (only 0.1 and 2 other version in the same level)
#1300 opened Nov 17, 2024 by moreAImore
8
SEO not helping ao topic: documentation Use this tag if this PR adds or improves documentation
#1298 opened Nov 16, 2024 by msaroufim
Why my QAT's convert doesn't work,still float32
#1290 opened Nov 15, 2024 by Xxxgrey
@andrewor14
5
ZeroPointDomain as an arguments
#1264 opened Nov 12, 2024 by airMeng
7
AMD integration tracker tracker
#1260 opened Nov 11, 2024 by jcaip
1 task
@petrex
1
Low bit shampoo enhancement New feature or request optimizer
#1257 opened Nov 9, 2024 by msaroufim
[QAT] Low-bit FSDP all-gather for QAT distributed good first issue Good for newcomers qat
#1224 opened Nov 5, 2024 by gau-nernst
1
Low Bit Optim Instability. optimizer
#1218 opened Nov 4, 2024 by nighting0le01
4
[Tracker] autoquant v2 tracker
#1215 opened Nov 1, 2024 by jerryzh168
CPUoffloadOptimizer issues bug Something isn't working optimizer
#1209 opened Nov 1, 2024 by felipemello1
4
[New method] VPTQ Vector Post-Training Quantization Support
#1204 opened Oct 31, 2024 by YangWang92
2
Does Float8Linear support Tensor Parallelism and Sequence Parallelism?
#1198 opened Oct 30, 2024 by zigzagcai
1
Add codebook (look up table based) quantization flow in torchao good first issue Good for newcomers
#1195 opened Oct 29, 2024 by jerryzh168
2
[low-bit optim] Add COAT optimizer good first issue Good for newcomers optimizer
#1190 opened Oct 29, 2024 by gau-nernst
5
torchao.float8 + torch.compile does not work on HuggingFace's Mixtral model
#1200 opened Oct 28, 2024 by vkuzo
7
Unable to save checkpoints when Use low bit optimizers with FSDP1 or FSDP2
#1185 opened Oct 28, 2024 by nighting0le01
3
[RFC] Follow Up for torchao developer experience discussion rfc
#1184 opened Oct 28, 2024 by jerryzh168
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.