executorch

executorch copied to clipboard

Add op: pixel_unshuffle

4

Differential Revision: D60978345

manuelcandales

Implement mm op for Arm backend

2

* Add legalization from aten.mm to TOSA MatMul for FP32 & INT8 types * Add tests for main and base inference * Add an annotator for aten.mm in the quantizer

tom-arm

Use single rounding as default for TOSA lowering

4

- Use single rounding at rescale to int8 - Minor refactor of op_addmm to use shared functions

SaoirseARM

Update pytorch pin

2

Updating PyTorch pin to Nightly 08/07/2024

mcr229

hello, now I want to realize the sliding window of kv cache, so dynamic allocation and reclamation of memory needs to be realized. could you please teach me how to...

l2002924700

Return zero number of elements for an empty tensor.

4

Summary: And use std lib to compute it. Differential Revision: D60854860

shoumikhin

Refactor delegation code

4

Summary: Refactoring partitioner-based delegation to prepare for allowing buffer mutations in the delegate (following diff). Differential Revision: D60813405

angelayi

Repeat op + pass expand -> repeat

1

Erik-Lundell

Add pass to convert split to many slice

1

Change-Id: I15f8a37fe88ba6c7d1e357c9ab897069c3c912b2

Erik-Lundell

Dummy change

1

Testing baseline full CI run for XNNPACK upgrade.

GregoryComer