-
Notifications
You must be signed in to change notification settings - Fork 119
Issues: pytorch/ao
[RFC] Which low bit CUDA kernels should we merge or write?
#697
opened Aug 17, 2024 by
msaroufim
Open
11
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
enable all the most recent ruff linter rules on torchao/float8 code
#1015
opened Oct 4, 2024 by
vkuzo
[easy] delete
torchao/float8/float8_aten_api.py
and move the functionality to float8_ops.py
#1014
opened Oct 4, 2024 by
vkuzo
Add weight tensor-wise scaling for INT8 quantized and mixed-precision training
enhancement
New feature or request
good first issue
Good for newcomers
#1010
opened Oct 4, 2024 by
gau-nernst
Make Quant-LLM compatible with BF16
enhancement
New feature or request
good first issue
Good for newcomers
inference
#998
opened Oct 3, 2024 by
gau-nernst
Create a quant_utils file to reduce code duplication in eval.py and generate.py
#992
opened Oct 2, 2024 by
jerryzh168
Does torch.export preserve the quantize_per_tensor/dequantize_per_tensor ops?
#986
opened Oct 1, 2024 by
justinchuby
How do I perform Int8 activation and int8 weight QAT and export to onnx?
#975
opened Sep 30, 2024 by
ben-da6
RuntimeError: CUDA error: named symbol not found CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with
TORCH_USE_CUDA_DSA
to enable device-side assertions.
#968
opened Sep 28, 2024 by
kolyan288
[MPS] torchao low-bit-precision optim does not expose 'backend' argument to torch.compile
good first issue
Good for newcomers
#955
opened Sep 26, 2024 by
bghira
[Question] Difference in MXLinear vs MXInferenceLinear grouping direction
#932
opened Sep 24, 2024 by
Abhijit-2592
installation fails on ARM64 Linux (aka Raspberry Pi 5)
multibackend
#913
opened Sep 21, 2024 by
sunshinesfbay
More fine-grained documentation needed for
torchao.autoquant()
#907
opened Sep 19, 2024 by
suvadityamuk
Previous Next
ProTip!
Follow long discussions with comments:>50.