executorch

executorch copied to clipboard

Quantization of yolov5 for XNNPACK backend

11

Hello, I want to quantize yolov5 model for XNNPACK backend on Intel CPU. So far, I confirmed following: 1. Exporting resnet18 into xnnpack-exported-resnet18.pte for XNNPACK backend. 2. Running xnnpack-resnet18.pte 3....

EarthMu

Added HiFi optimizations for add sub mul and div operators

2

Added HiFi optimizations for add sub mul and div operators

cad-audio

Update README.md

2

#### Summary abc xyz Closes # #### Test plan abc xyz aaa

dvorjackz

Pte export of llama model

3

### 🐛 Describe the bug python -m examples.models.llama2.export_llama --checkpoint "${MODEL_DIR}/model.pth" -p "${MODEL_DIR}/original/params.json" -kv --disable_dynamic_shape --qnn --pt2e_quantize qnn_16a4w -d fp32 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --soc_model SM8650 --output_name="test.pte" nomodule error ModuleNotFoundError: No...

Vinaysukhesh98

Add compatible HuggingFace models to benchmark workflow

11

guangy10

Integrating Axis Mapping into Quantized Linear Texture Implementation

5

Summary: # Summary Integrating Axis Mapping into Quantized Linear texture implementation following D62518403. This updates the Quantized Linear shader to map the virtual texture axis to the logical texture axis....

kushrast

Add event tracing and ETDumps to executor_runner

15

- Enabled via EXECUTORCH_ENABLE_EVENT_TRACER - Add flag 'etdump_path' to specify the file path for the ETDump file - Add flag 'num_executions' for number of iterations to run - Create and...

benkli01