Search results

Tensor subclass slice during <code>inference_mode</code> fails

inference modeEverything related to InferenceMode guardEverything related to InferenceMode guard

module: dispatchDispatchStub, Type, void pointer table, c10 dispatchDispatchStub, Type, void pointer table, c10 dispatch

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

tensor subclassRelated to tensor subclassesRelated to tensor subclasses

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

Bug

#164872 In pytorch/pytorch;

· andrewor14 opened on Oct 7, 2025

qta and export onnx error

module: onnxRelated to torch.onnxRelated to torch.onnx

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164116 In pytorch/pytorch;

· WangHHY19931001 opened on Sep 29, 2025

CPU dynamic quantization (qint8) cannot be used with multiprocessing

module: cpuCPU specific problem (e.g., perf, algorithm)CPU specific problem (e.g., perf, algorithm)

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#163052 In pytorch/pytorch;

· ytinyui opened on Sep 16, 2025

heap-buffer-overflow in torch.quantized_max_pool2d via Python API

module: crashProblem manifests as a hard crash, as opposed to a RuntimeErrorProblem manifests as a hard crash, as opposed to a RuntimeError

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#162476 In pytorch/pytorch;

· cx104906 opened on Sep 9, 2025

<code>dequantize_per_channel</code> in <code>quantized_decomposed</code> not compatible with Float8 types

module: floatx (formerly float8)For torch.float8_e5m2 and torch.float8_e4m3 and other sub 8-bit float typesFor torch.float8_e5m2 and torch.float8_e4m3 and other sub 8-bit float types

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#160651 In pytorch/pytorch;

· heglex opened on Aug 14, 2025

torch.quantize_per_tensor not implemented for SparseCPU tensors

module: sparseRelated to torch.sparseRelated to torch.sparse

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#160631 In pytorch/pytorch;

· springcrane opened on Aug 14, 2025

NotImplementedError: Could not run 'aten::q_scale' with arguments from the 'CPU'

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#159743 In pytorch/pytorch;

· djxnqp opened on Aug 4, 2025

Cannot pass through None for example_inputs in prepare_fx

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

Status: Open.

#159505 In pytorch/pytorch;

· rjgleaton opened on Jul 30, 2025

[dynamo] Missing meta kernel for <code>aten::quantize_per_tensor.tensor_qparams</code>

module: dynamo

oncall: pt2

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#157729 In pytorch/pytorch;

· StrongerXi opened on Jul 7, 2025

PT2E Quantization Migration Tracker

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#157591 In pytorch/pytorch;

· jerryzh168 opened on Jul 3, 2025

ConvertTritonGPUToLLVM pass fails on fused GroupNorm backward (SM 89) under torch.compile(…, backend='inductor')

oncall: cpu inductorCPU Inductor issues for Intel team to triageCPU Inductor issues for Intel team to triage

oncall: pt2

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#156549 In pytorch/pytorch;

· AK-1996 opened on Jun 21, 2025

intmm is being compiled inconsistently with errors.

module: inductor

oncall: pt2

oncall: quantizationQuantization support in PyTorchQuantization support in PyTorch

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#155838 In pytorch/pytorch;

· HDCharles opened on Jun 12, 2025