Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Accept mx.array type for prompt argument for stream_generate #1125

Merged
merged 2 commits into from
Nov 27, 2024
Merged

Accept mx.array type for prompt argument for stream_generate #1125

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
152d6b1
Accept mx.array type for prompt argument for stream_generate
neilmehta24 Nov 26, 2024
83bc764
Fix formatting
neilmehta24 Nov 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions llms/mlx_lm/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,7 +298,7 @@ def _step(y):
def stream_generate(
model: nn.Module,
tokenizer: Union[PreTrainedTokenizer, TokenizerWrapper],
prompt: Union[str, List[int]],
prompt: Union[str, mx.array, List[int]],
max_tokens: int = 100,
**kwargs,
) -> Generator[GenerationResponse, None, None]:
Expand All @@ -308,7 +308,7 @@ def stream_generate(
Args:
model (nn.Module): The model to use for generation.
tokenizer (PreTrainedTokenizer): The tokenizer.
prompt (Union[str, List[int]]): The input prompt string or integer tokens.
prompt (Union[str, mx.array, List[int]]): The input prompt string or integer tokens.
max_tokens (int): The maximum number of tokens. Default: ``100``.
kwargs: The remaining options get passed to :func:`generate_step`.
See :func:`generate_step` for more details.
Expand All @@ -320,7 +320,11 @@ def stream_generate(
if not isinstance(tokenizer, TokenizerWrapper):
tokenizer = TokenizerWrapper(tokenizer)

prompt = mx.array(prompt if isinstance(prompt, list) else tokenizer.encode(prompt))
if not isinstance(prompt, mx.array):
prompt = mx.array(
prompt if isinstance(prompt, list) else tokenizer.encode(prompt)
)

detokenizer = tokenizer.detokenizer

with wired_limit(model, [generation_stream]):
Expand Down