executorch

executorch copied to clipboard

[Core ML] Implement intermediate tensor logging

2

- Updated `ModelEventLoggerImpl ` to log intermediate tensor values. - Updated `sdk_example_runner` to build `Core ML` when specified. - Added `debugger_cli` script to compare intermediate tensor values of a program...

cymbalrush

### 🐛 Describe the bug Follow up guide here: https://pytorch.org/executorch/main/build-run-qualcomm-ai-engine-direct-backend.html#setting-up-your-developer-environment Then run `./backends/qualcomm/scripts/build.sh --release`, will hit the error: ``` ~/executorch/examples/qualcomm/llama2/qaihub_runner/runner.cpp:21:10: fatal error: 'executorch/examples/models/llama2/runner/util.h' file not found 21 | #include |...

guangy10

Do not print eos

2

Summary: We don't want to print eos in the response because some eos tokens could be ``. Differential Revision: D61048254

helunwencser

[llava][18/N] Move token generation loop to a class

2

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * __->__ #4652 As titled. This PR moves the token generation loop in llama2 runner into a new class so it can be reused....

larryliu0820

[executorch] Migrate runtime/core to new namespace

4

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #4621 * #4620 * #4619 * #4618 * #4617 * #4616 * #4615 * #4614 * #4613 * #4612 * #4611 * #4610...

dbort

allow models to use customized token ids during export

4

LLama3.1's [bos and eos](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/blob/main/tokenizer_config.json) are different from what is hardcoded in the code. This PR updates the export flow to allow read customized token ids instead of hardcoded ones. It...

helunwencser

Run trunk.yml when we update PT pin

3

So that macos can be covered

kirklandsign

[executorch] Migrate extension/test_utils to new namespace

5

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #4621 * #4620 * #4619 * #4618 * __->__ #4617 * #4616 * #4615 * #4614 * #4613 * #4612 * #4611 *...

dbort

[executorch] Migrate runtime/backend to new namespace

5

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #4621 * #4620 * #4619 * #4618 * #4617 * #4616 * #4615 * #4614 * __->__ #4613 * #4612 * #4611 *...

dbort

[executorch] Migrate runtime/platform tests to new namespace

4

Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #4621 * #4620 * #4619 * #4618 * #4617 * #4616 * #4615 * #4614 * #4613 * #4612 * #4611 * #4610...

dbort