You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
de2475f31c
This PR drops custom generation codes and introduces compatibility with `transformers.GenerationMixin` instead. This includes support for more sampling options (`top_p`, `top_k`, `repetition_penalty` requested in #460) and beam search - all that is now identical to running model with transformers locally. Most features (excluding beam search and other rarely used stuff) are also compatible with resuming existing sessions. ### Breaking changes If `.generate()` or forward passes are being run inside an `.inference_session()` context, they now use the opened session by default. So, these snippets are now equivalent: ```python # Using default session with model.inference_session(max_length=100): output_ids = model.generate(input_ids, max_new_tokens=3) # Explicitly specifying a session with model.inference_session(max_length=100) as sess: output_ids = model.generate(input_ids, max_new_tokens=3, session=sess) ``` Earlier, the 1st snippet was creating a new session, which is not what most people expected (= such code was most likely to introduce a bug, which is now fixed). |
9 months ago | |
---|---|---|
.. | ||
bootstrap.id | 10 months ago | |
conftest.py | 1 year ago | |
server2.id | 10 months ago | |
test_aux_functions.py | 9 months ago | |
test_block_exact_match.py | 9 months ago | |
test_chained_calls.py | 10 months ago | |
test_dtype.py | 11 months ago | |
test_full_model.py | 9 months ago | |
test_peft.py | 10 months ago | |
test_priority_pool.py | 1 year ago | |
test_remote_sequential.py | 9 months ago | |
test_sequence_manager.py | 10 months ago | |
test_server_stats.py | 10 months ago | |
test_tensor_parallel.py | 10 months ago | |
test_utils.py | 10 months ago |