Save the built engine on a single GPU to the given path.
(
self,
model: _ModelRuntimeContext,
model_dir: str,
engine_dir: str,
)
| 285 | return self._model_format |
| 286 | |
| 287 | def save( |
| 288 | self, |
| 289 | model: _ModelRuntimeContext, |
| 290 | model_dir: str, |
| 291 | engine_dir: str, |
| 292 | ): |
| 293 | ''' Save the built engine on a single GPU to the given path. ''' |
| 294 | model.engine.save(engine_dir) |
| 295 | if model.mapping.rank == 0: |
| 296 | tokenizer = ModelLoader.load_hf_tokenizer( |
| 297 | model_dir, |
| 298 | trust_remote_code=self.llm_args.trust_remote_code, |
| 299 | use_fast=self.llm_args.tokenizer_mode != 'slow') |
| 300 | if tokenizer is not None: |
| 301 | tokenizer.save_pretrained(engine_dir) |
| 302 | |
| 303 | def _download_hf_model(self): |
| 304 | ''' Download HF model from third-party model hub like www.modelscope.cn or huggingface. ''' |
no test coverage detected