Skip to content

Pull requests: pytorch/executorch

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
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[ExecuTorch][llm] Wire --use_moe_quantized_op through export pipeline and LLM config CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21540 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add MoE quantized custom op documentation CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21539 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Fuse w1+w3 into single GEMM in quantized_moe_ffn CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21538 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add numerical kernel tests for quantized_moe_ffn CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21537 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21536 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add MoE source transformation with INT4 quantized packing CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21535 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add Meta kernel and registration probe for quantized_moe_ffn CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21534 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[ExecuTorch][llm] Add quantized_moe_ffn custom op with C++ kernel CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21533 opened Jul 31, 2026 by pytorchbot Collaborator Loading…
[MLX] Add off-graph KV cache ring runtime CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21532 opened Jul 31, 2026 by kiymetakdemir Contributor Loading…
Ship the CUDA delegate as its own library CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21531 opened Jul 31, 2026 by shoumikhin Contributor Loading…
Ship the XNNPACK delegate as its own library CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21526 opened Jul 31, 2026 by shoumikhin Contributor Loading…
Ship the merged CPU kernels as their own library CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21524 opened Jul 31, 2026 by shoumikhin Contributor Loading…
xplat/executorch/tools/buck/constraints/BUCK CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported
#21523 opened Jul 31, 2026 by meta-codesync Bot Loading…
Ship the thread pool as its own library so a process has one pool CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21522 opened Jul 31, 2026 by shoumikhin Contributor Loading…
Arm backend: Add serialised xlarge VKML model suite ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: arm Issues related to arm backend partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: arm Changes to the ARM backend delegate
#21518 opened Jul 31, 2026 by bdemirb Collaborator Loading…
Fix out-of-bounds traversal in reduce_util for non-contiguous tensors CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: kernels Issues related to kernel libraries and utilities, and code under kernels/ release notes: ops & kernels Changes to the opset and any new / changed kernel implementations
#21517 opened Jul 31, 2026 by SuryanshSS1011 Contributor Loading…
NXB backend: Add recipes for Neutron backend lowering. CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate
#21516 opened Jul 31, 2026 by MartinPavella Collaborator Loading…
NXP backend: added support for aten.pad with mode reflect CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ release notes: nxp Changes to the NXP Neutron backend delegate
#21515 opened Jul 31, 2026 by novak-vaclav Collaborator Loading…
Ship a linkable shared runtime and make the Python bindings use it ciflow/binaries/all Release PRs with this label will build wheels for all python versions ciflow/binaries ciflow/cuda ciflow/nightly ciflow/periodic ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21514 opened Jul 31, 2026 by shoumikhin Contributor Loading…
[ExecuTorch][Core AI][5/x] Enumerated input-shape support CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21513 opened Jul 31, 2026 by metascroy Contributor Loading…
[ExecuTorch][Core AI][4/x] Export recipes (fp32/fp16) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21512 opened Jul 31, 2026 by metascroy Contributor Loading…
[ExecuTorch][Core AI][3/x] PT2E quantizer front-end CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21511 opened Jul 31, 2026 by metascroy Contributor Loading…
[ExecuTorch][Core AI][2/x] Core backend: partitioner, preprocess, IO compat, copy-op pass CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21510 opened Jul 31, 2026 by metascroy Contributor Loading…
[ExecuTorch][Core AI][1/x] Graph pass: int64/float64 dtype narrowing CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#21509 opened Jul 31, 2026 by metascroy Contributor Loading…
Keep delegate-consumed mutable buffers above the delegate (#21507) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. meta-exported
#21507 opened Jul 30, 2026 by Conarnar Contributor Loading…
ProTip! Adding no:label will show everything without a label.