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

233 Open 223 Closed
233 Open 223 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

AO/GemLite tensors produce incorrect outputs in vLLM
#2141 opened Apr 28, 2025 by mobicham
QAT model drops accuracy after converting with torch.ao.quantization.convert
#2138 opened Apr 28, 2025 by tranngocduvnvp
Conda recipe? binaries
#2137 opened Apr 27, 2025 by sarthakpati
2
int8 quantization with FSDP for inference error
#2127 opened Apr 25, 2025 by Andy0422
Question about dtype check in marlin_qqq validation for w4a8 functionality
#2115 opened Apr 23, 2025 by xxw11
1
[PT2E] observers do not handle inputs with different shapes correctly
#2112 opened Apr 23, 2025 by Xia-Weiwen
@jerryzh168
10
Got unexpected low speed using quantization inference on qwen models.
#2102 opened Apr 22, 2025 by HaoKang-Timmy
2
[Tracker] TorchAO activation sparsity acceleration 🚀
#2095 opened Apr 22, 2025 by jcaip
2 of 9 tasks
@jcaip
[Quant][PT2E] AffineQuantized observers failed Resnet18
#2094 opened Apr 22, 2025 by Xia-Weiwen
@jerryzh168
1
Deprecate/Remove GPTQ.py
#2089 opened Apr 21, 2025 by jerryzh168
1
How to automatically install the latest TorchAO nightly wheel
#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
#2078 opened Apr 18, 2025 by jainapurva
1
Dynamo error with large mesh + AdamWFp8 + bf16 stochastic rounding bug Something isn't working distributed optimizer
#2074 opened Apr 18, 2025 by cassanof
1
Make lm_eval optional dependency
#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
#2056 opened Apr 14, 2025 by jerryzh168
@HDCharles
Making RCEIL the default for MXFP scale derivation mx
#2035 opened Apr 10, 2025 by frsun-nvda
Fix remaining issues when running on H100 machines
#2028 opened Apr 8, 2025 by jerryzh168
@jerryzh168 @drisspg
1
Failed to save the static quantized model quantize
#1950 opened Mar 25, 2025 by yiliu30
3
cast to mxfp8 across dim1 should be performant float8
#1945 opened Mar 24, 2025 by vkuzo
Torchao import time
#1944 opened Mar 24, 2025 by felipemello1
1
[Bug] FSDP2 FP8 compatibility problem with nn.Linear layers (GPU count > out_features) distributed float8
#1938 opened Mar 24, 2025 by HIT-cwh
4
FSDP2 + CPU Offload + AdamW8bit issue
#1931 opened Mar 21, 2025 by psinger
2
Torchao's CPU overhead counteracts the performance benefit of using quantization kernel.
#1930 opened Mar 21, 2025 by LuFinch
11
fp8 quantization with FSDP2 error
#1929 opened Mar 20, 2025 by happynear
4
Does torchao support FP8 Grouped GEMM? float8
#1928 opened Mar 20, 2025 by zigzagcai
5
ProTip! Type g i on any issue or pull request to go back to the issue listing page.