Skip to content

[Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) #16631

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 2 commits into from
Apr 15, 2025
Merged

[Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) #16631

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2c06815
Fix broken GritLM model and tests
pooyadavoodi Apr 15, 2025
bec5700
Fix pre-commit
pooyadavoodi Apr 15, 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
21 changes: 11 additions & 10 deletions tests/models/embedding/language/test_gritlm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,24 +57,25 @@ def test_find_array(monkeypatch: pytest.MonkeyPatch):
def server_embedding():
# GritLM embedding implementation is only supported by XFormers backend.
args = ["--task", "embed", "--max_model_len", str(MAX_MODEL_LEN)]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server
with pytest.MonkeyPatch.context() as m:
m.setenv(STR_BACKEND_ENV_VAR, "XFORMERS")
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server


@pytest.fixture(scope="module")
def server_generate():
args = ["--task", "generate", "--max_model_len", str(MAX_MODEL_LEN)]
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server
with pytest.MonkeyPatch.context() as m:
m.setenv(STR_BACKEND_ENV_VAR, "XFORMERS")
with RemoteOpenAIServer(MODEL_NAME, args) as remote_server:
yield remote_server


@pytest_asyncio.fixture
async def client_embedding(monkeypatch: pytest.MonkeyPatch,
server_embedding: RemoteOpenAIServer):
with monkeypatch.context() as m:
m.setenv("VLLM_ATTENTION_BACKEND", "XFORMERS")
async with server_embedding.get_async_client() as async_client:
yield async_client
async def client_embedding(server_embedding: RemoteOpenAIServer):
async with server_embedding.get_async_client() as async_client:
yield async_client


@pytest_asyncio.fixture
Expand Down
3 changes: 2 additions & 1 deletion vllm/model_executor/models/gritlm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,8 @@ def forward(
mean_embeddings = sum_embeddings / num_non_instruction_tokens.unsqueeze(
1)

pooled_data = self.head(mean_embeddings)
pooled_data = self.head(mean_embeddings,
pooling_metadata=pooling_metadata)

pooled_outputs = [
PoolingSequenceGroupOutput(data) for data in pooled_data
Expand Down