Skip to content

Issues: pytorch/ao

[RFC] torchao Contributor Guide
#391 opened Jun 18, 2024 by jerryzh168
Open 16
low precision training upcoming feature tracker
#556 opened Jul 30, 2024 by vkuzo
Open 2
Multibackend tracker
#1082 opened Oct 15, 2024 by msaroufim
Open
Beta
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

232 Open 231 Closed
232 Open 231 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

nightly build for mac stops on 0422 distribution triaged
#2157 opened May 1, 2025 by guangy10
@atalman
4
python setup.develop is taking a lot of time build triaged
#2150 opened Apr 29, 2025 by anijain2305
@atalman
1
[tracker] Low precision training for MoEs tracker triaged
#2147 opened Apr 29, 2025 by danielvegamyhre
4 of 10 tasks
1
KleidiAI int4 kernels not loading properly on aarch64 Linux quantize triaged
#2143 opened Apr 28, 2025 by vctrmn
@metascroy
3
AO/GemLite tensors produce incorrect outputs in vLLM integration Issues related to integrations with other libraries, like huggingface, vllm, sglang, gemlite etc. quantize triaged
#2141 opened Apr 28, 2025 by mobicham
AssertionError During Quantization of torch.empty_like(), torch.ones_like, and torch.randn_like pt2e_quant pt2 export quantization triaged
#2146 opened Apr 28, 2025 by defaultd661
2
QAT model drops accuracy after converting with torch.ao.quantization.convert qat triaged
#2138 opened Apr 28, 2025 by tranngocduvnvp
@andrewor14
3
int8 quantization with FSDP for inference error distributed quantize triaged
#2127 opened Apr 25, 2025 by Andy0422
2
Question about dtype check in marlin_qqq validation for w4a8 functionality quantize triaged
#2115 opened Apr 23, 2025 by xxw11
1
[PT2E] observers do not handle inputs with different shapes correctly pt2e_quant pt2 export quantization triaged
#2112 opened Apr 23, 2025 by Xia-Weiwen
@Xia-Weiwen
12
Got unexpected low speed using quantization inference on qwen models. performance triaged
#2102 opened Apr 22, 2025 by HaoKang-Timmy
@jerryzh168
2
[Tracker] TorchAO activation sparsity acceleration 🚀 sparsity tracker triaged
#2095 opened Apr 22, 2025 by jcaip
2 of 9 tasks
@jcaip
[Quant][PT2E] AffineQuantized observers failed Resnet18 pt2e_quant pt2 export quantization triaged
#2094 opened Apr 22, 2025 by Xia-Weiwen
@jerryzh168 @Xia-Weiwen
1
Deprecate/Remove GPTQ.py quantize tracker triaged
#2089 opened Apr 21, 2025 by jerryzh168
2
How to automatically install the latest TorchAO nightly wheel distribution triaged
#2086 opened Apr 21, 2025 by MingxuZh
@atalman
1
Refactor torchao and tests to use model architectures from torchao.testing.model_architectures good first issue Good for newcomers triaged
#2078 opened Apr 18, 2025 by jainapurva
1
Dynamo error with large mesh + AdamWFp8 + bf16 stochastic rounding bug Something isn't working distributed optimizer triaged
#2074 opened Apr 18, 2025 by cassanof
1
Make lm_eval optional dependency topic: for developers Use this tag if this PR is mainly developer facing triaged
#2073 opened Apr 18, 2025 by jainapurva
@jainapurva
Remove old subclass implementation to reduce maintainence cost topic: deprecation Use this tag if this PR deprecates a feature triaged
#2056 opened Apr 14, 2025 by jerryzh168
@HDCharles
Making RCEIL the default for MXFP scale derivation mx triaged
#2035 opened Apr 10, 2025 by frsun-nvda
1
Fix remaining issues when running on H100 machines topic: for developers Use this tag if this PR is mainly developer facing triaged
#2028 opened Apr 8, 2025 by jerryzh168
@jerryzh168 @jainapurva @drisspg
1
cast to mxfp8 across dim1 should be performant float8 triaged
#1945 opened Mar 24, 2025 by vkuzo
Torchao import time topic: improvement Use this tag if this PR is an improvement (doesn't fit into any of the other categories) triaged
#1944 opened Mar 24, 2025 by felipemello1
@msaroufim
3
[Bug] FSDP2 FP8 compatibility problem with nn.Linear layers (GPU count > out_features) distributed float8 triaged
#1938 opened Mar 24, 2025 by HIT-cwh
5
FSDP2 + CPU Offload + AdamW8bit issue optimizer triaged
#1931 opened Mar 21, 2025 by psinger
@gau-nernst
2
ProTip! Mix and match filters to narrow down what you’re looking for.