-
Notifications
You must be signed in to change notification settings - Fork 599
Pull requests: pytorch/executorch
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Arm backend: Build c/c++ code with -Wall -Werror
ciflow/trunk
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
partner: arm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm
release notes: none
Do not include this in the release notes
#11815
opened Jun 19, 2025 by
zingo
Loading…
Update export_llama in READMEs to use export_llm
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11811
opened Jun 19, 2025 by
jackzhxng
Loading…
Get rid of llm_config enums
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11810
opened Jun 19, 2025 by
jackzhxng
Loading…
Ability to specify full file configs from anywhere
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11809
opened Jun 19, 2025 by
jackzhxng
Loading…
Fix static attention non-HF RoPE implementation
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
topic: not user facing
#11808
opened Jun 19, 2025 by
sxu
Loading…
[XNNPACK] Add support for Linear fused BatchNorm
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: none
Do not include this in the release notes
#11805
opened Jun 19, 2025 by
keyprocedure
Loading…
Add tanh op to XNNPACK backend
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: none
Do not include this in the release notes
#11804
opened Jun 18, 2025 by
leafs1
Loading…
Support exp op in XNNPACK backend
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: none
Do not include this in the release notes
#11803
opened Jun 18, 2025 by
leafs1
Loading…
Re-reapply "Add vectorized_math.h (#11204)", "Add optimized_portable_kernels test (#11205)", and "Add vectorization in elementwise_util (#9432)"
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
#11802
opened Jun 18, 2025 by
swolchok
Loading…
Enable sleef in xplat_exported_deps of aten_headers_for_executorch
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
#11801
opened Jun 18, 2025 by
swolchok
Loading…
Pull c10 headers directly from PyTorch internally, not from the c10 mirror
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
#11800
opened Jun 18, 2025 by
swolchok
Loading…
Fix bug in sub op to ignore alpha != 1 (fixes: #11684)
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: xnnpack
Changes to the XNNPack backend delegate
#11796
opened Jun 18, 2025 by
abhinaykukkadapu
Loading…
downgrade flatbuffers in oss
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
Add last_token_pos in llama_transformer
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
#11793
opened Jun 18, 2025 by
sdwilsh
Loading…
Bump pinned PT commit to 20250616 and mirror torch/standalone to ExecuTorch
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
fb-exported
release notes: none
Do not include this in the release notes
#11791
opened Jun 18, 2025 by
swolchok
Loading…
Qualcomm AI Engine Direct - support cli
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
partner: qualcomm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#11788
opened Jun 18, 2025 by
haowhsu-quic
Loading…
Rename CMake target 'executorch' to 'prim_ops_lib' for clarity
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: build
Changes related to build, including dependency upgrades, build flags, optimizations, etc.
#11786
opened Jun 18, 2025 by
JawadKhan65
Loading…
NXP backend: Add quantization of aten.view
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
#11784
opened Jun 18, 2025 by
robert-kalmar
•
Draft
Arm backend: Replace Tensor_Scalar with Tensor_Tensor in sqrt op
ciflow/trunk
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
partner: arm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm
release notes: arm
Changes to the ARM backend delegate
#11783
opened Jun 18, 2025 by
wwwind
Loading…
Qualcomm AI Engine Direct - Delegate mutable buffer and fix the mutable buffer issue
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
partner: qualcomm
For backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
#11782
opened Jun 18, 2025 by
shewu-quic
Loading…
Implement python deserialize for flat_tensor
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: none
Do not include this in the release notes
#11779
opened Jun 18, 2025 by
GregoryComer
Loading…
Fix bug in add op to ignore alpha != 1 (fixes: #11683)
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
release notes: xnnpack
Changes to the XNNPack backend delegate
#11777
opened Jun 18, 2025 by
abhinaykukkadapu
Loading…
[XNNPACK Quantizer] Select between TConvs and Convs
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11776
opened Jun 18, 2025 by
pytorchbot
Loading…
[Quantized DeConv Support] Dynamically Quantized Deconvolutions with groups ==1
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11775
opened Jun 18, 2025 by
pytorchbot
Loading…
[Quantized DeConv Support] Enable Quantized Transposed Convs with groups==1
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#11774
opened Jun 18, 2025 by
pytorchbot
Loading…
Previous Next
ProTip!
Exclude everything labeled
bug
with -label:bug.