[XNNPACK Quantizer] Select between TConvs and Convs#11863

Open

GregoryComer wants to merge 80 commits intogh/mcr229/32/origfrom

gh/mcr229/33/orig

Commits on Jun 17, 2025

Fix for overriding installed executorch when running optimum-et models (#11745)

guangy10
and
Guang Yang
authored
Update documents for buffer allocator (#11467)
neuropilot-captain
authored
Add function for input preprocessing in numerical comparator
Juntian Liu
authored
[llm] Add generate_from_pos API to LLM runner (#11570)
larryliu0820
authored
Arm backend: Added decomposition for MaxPool2d with dilation > 0. (#11724)
wwwind
authored
Arm backend: Add support for per-channel quantization (#11752)
oscarandersson8218
authored
Arm backend: Fix bug in decompose linear vector norm (#11755)
wwwind
authored
Add numerical comparator base class and L1 comparator
Juntian Liu
authored
Fix text_llm_runner unit test
larryliu0820
authored
Use wrappers from xnnpack.h for unary and binary ops (#11584) (#11666)
abhinaykukkadapu
authored
Qualcomm AI Engine Direct - GA Albert, Bert, Distilbert, Eurobert (#11546)
winskuo-quic
authored
Qualcomm AI Engine Direct - Deprecate convert_bmm_to_matmul pass (#11392)
DannyYuyang-quic
authored
Add MSE numerical comparator
Juntian Liu
authored
Refactor XNNPACK tester to extract delegate-independent tester classes (#11596)
GregoryComer
authored
Reapply D74208085: "Switch fbcode builds of ExecuTorch and PyTorch to fbsource sleef (#11261)" (#11765)

pytorchbot
and
swolchok
authored
[ET-VK][Ops] quantization op shaders and impl (#11767)

pytorchbot
and
morelos
authored
[ET-VK][Ops] dequantization op shaders and impl (#11768)
pytorchbot
authored
[ET-VK][Ops] choose_qparams op shaders and impl (#11769)
pytorchbot
authored
skip et quantizer numeric debugging tests for infra update
Gasoonjia
authored

Commits on Jun 18, 2025

Commits on Jun 19, 2025

Commits on Jun 20, 2025

Commits on Jun 21, 2025

Commits on Jun 23, 2025