-
Notifications
You must be signed in to change notification settings - Fork 1.2k
All issues
Issue creation is restricted in this repository
- #7679 · mergennachin opened
on Jan 15, 2025 - #22188 · JacobSzwejbka opened
on Aug 26, 2026 5
Issues
is:issue state:open
is:issue state:open
Search results
[Tracking] Complete audio task coverage across CPU, GPU, and NPU backends
enhancementNot as big of a feature, but technically not a bug. Should be easy to fixNot as big of a feature, but technically not a bug. Should be easy to fixmodule: examplesIssues related to demos under examples/Issues related to demos under examples/Status: Open.#23164 In pytorch/executorch;Qualcomm: 8-bit per-channel weight scales are floored at the 16-bit eps, and the HTP miscomputes near-zero channels
module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommStatus: Open.#23160 In pytorch/executorch;[cpu kernels] native_layer_norm: layer_norm_scalar returns NaN on large-mean rows; Half/BF16 at N>=256 slow after #23153
module: kernelsIssues related to kernel libraries and utilities, and code under kernels/Issues related to kernel libraries and utilities, and code under kernels/Status: Open.#23159 In pytorch/executorch;[Vulkan] scalar_tensor uploads float bytes to integer scalar shaders
module: vulkanIssues related to the Vulkan delegate and code under backends/vulkan/Issues related to the Vulkan delegate and code under backends/vulkan/Status: Open.#23158 In pytorch/executorch;[Vulkan] Missing/partial op support blocks full delegation of a dynamic-shape transformer encoder
module: vulkanIssues related to the Vulkan delegate and code under backends/vulkan/Issues related to the Vulkan delegate and code under backends/vulkan/Status: Open.#23156 In pytorch/executorch;Enable Nemotron-3-Diarization on MLX, CUDA, XNNPACK, and Vulkan
enhancementNot as big of a feature, but technically not a bug. Should be easy to fixNot as big of a feature, but technically not a bug. Should be easy to fixmodule: cudaIssues related to the AOTI CUDA backendIssues related to the AOTI CUDA backendmodule: examplesIssues related to demos under examples/Issues related to demos under examples/module: mlxIssues related to MLX Backend: Metal-accelerated inference on Apple SiliconIssues related to MLX Backend: Metal-accelerated inference on Apple Siliconmodule: vulkanIssues related to the Vulkan delegate and code under backends/vulkan/Issues related to the Vulkan delegate and code under backends/vulkan/module: xnnpackIssues related to xnnpack delegation and the code under backends/xnnpack/Issues related to xnnpack delegation and the code under backends/xnnpack/Status: Open.#23131 In pytorch/executorch;Qualcomm: 16a16w quantization is much less accurate than 16a8w
module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/module: quantizationIssues related to quantizationIssues related to quantizationStatus: Open.#23108 In pytorch/executorch;Enable native Kev inference with the WebGPU backend
good first issueGood for newcomersGood for newcomersmodule: examplesIssues related to demos under examples/Issues related to demos under examples/module: webgpuIssues relating to WebGPU backendIssues relating to WebGPU backendStatus: Open.#23099 In pytorch/executorch;Enable native Kev inference with the Vulkan backend
good first issueGood for newcomersGood for newcomersmodule: examplesIssues related to demos under examples/Issues related to demos under examples/module: vulkanIssues related to the Vulkan delegate and code under backends/vulkan/Issues related to the Vulkan delegate and code under backends/vulkan/Status: Open.#23098 In pytorch/executorch;Enable native Kev inference with the AOTI CUDA backend
good first issueGood for newcomersGood for newcomersmodule: cudaIssues related to the AOTI CUDA backendIssues related to the AOTI CUDA backendmodule: examplesIssues related to demos under examples/Issues related to demos under examples/Status: Open.#23097 In pytorch/executorch;Qualcomm: HTP hangs in fp16 on a dilated conv when the dilated extent exceeds the input and cin is large
module: qnnIssues related to Qualcomm's QNN delegate and code under backends/qualcomm/Issues related to Qualcomm's QNN delegate and code under backends/qualcomm/partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommtriagedThis 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 moduleStatus: Open.#23096 In pytorch/executorch;- Status: Open.#23058 In pytorch/executorch;