jianan-gu
|
3b29c9fdb7
|
Extend Transformers Trainer Class to Enable PyTorch Torchscript for Inference (#17153)
* add jit mode option and model wrap
* Update src/transformers/training_args.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* Update src/transformers/training_args.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* refine code
* Update src/transformers/trainer.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* Update src/transformers/trainer.py
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* add ut and refine code
* code refine
* refine code
* add inference doc
* Update src/transformers/trainer.py
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* Update src/transformers/trainer.py
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* add cpu inference performance doc
* Update perf_infer_cpu.mdx
* Update perf_infer_cpu.mdx
* Update performance.mdx
* Update _toctree.yml
* refine jit func naming
* Update _toctree.yml
* Delete perf_infer_gpu_one.mdx
* Update perf_infer_cpu.mdx
* Update docs/source/en/perf_infer_cpu.mdx
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
* add none check before jit
* Update docs/source/en/perf_infer_cpu.mdx
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
* Update docs/source/en/perf_infer_cpu.mdx
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Stas Bekman <stas@stason.org>
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
|
2022-06-14 07:56:47 -04:00 |
|