Skip to content

Use granite-io async interface #936

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

Merged
merged 5 commits into from
May 2, 2025
Merged

Use granite-io async interface #936

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c5a34f8
Use granite-io async interface
mandel May 2, 2025
433f053
Revert changes to pdl/__init__.py
mandel May 2, 2025
e9042cc
Undo previous commit
mandel May 2, 2025
40e4867
Formatting
mandel May 2, 2025
b5080e4
Merge branch 'main' into pdl-272
mandel May 2, 2025
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
6 changes: 4 additions & 2 deletions src/pdl/pdl_granite_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ def processor_of_block(block: GraniteioModelBlock):
assert isinstance(model, str), f"The model should be a string: {model}"
assert isinstance(
backend, (dict, str)
), f"The backend should be a string or a dictionnary: {backend}"
), f"The backend should be a string or a dictionary: {backend}"
match backend:
case {"transformers": device}:
assert isinstance(backend, dict)
Expand Down Expand Up @@ -83,7 +83,9 @@ async def async_generate_text(
assert parameters is None or isinstance(parameters, dict)
io_processor = GraniteioModel.processor_of_block(block)
inputs = GraniteioModel.build_message(messages, parameters)
result = io_processor.create_chat_completion(inputs) # pyright: ignore
result = await io_processor.acreate_chat_completion( # pyright: ignore
inputs
)
try: # TODO: update when new version of granite-io is released
message = result.next_message.model_dump()
except AttributeError:
Expand Down