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

Remove bad check #683

Merged
merged 2 commits into from
Nov 15, 2024
Merged

Remove bad check #683

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
2b247de
remove
magdyksaleh Nov 15, 2024
42f4901
fix
magdyksaleh Nov 15, 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
2 changes: 1 addition & 1 deletion server/lorax_server/models/custom_modeling/flash_gemma2_modeling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,7 +501,7 @@ def forward(


class FlashGemma2ForCausalLM(torch.nn.Module):
def __init__(self, prefix, config, weights, causal: bool):
def __init__(self, prefix, config, weights, causal=True):
super().__init__()
self.config = config

Expand Down
12 changes: 2 additions & 10 deletions server/lorax_server/models/flash_causal_lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1114,15 +1114,6 @@ def __init__(
weights._set_config(model_id, config)

self._supports_embeddings = embedding_dim is not None
if (
not (weights.has_tensor("lm_head.weight") or weights.has_tensor("language_model.lm_head.weight"))
and not self._supports_embeddings
):
raise ValueError(
"Model does not have lm head so it is presumed to be for embeddings."
"No embedding_dim was provided so we cannot load the model."
"Please pass in an embedding_dim to the model."
)

prefix = ""
model = model_cls(prefix, config, weights)
Expand Down Expand Up @@ -1750,7 +1741,8 @@ def generate_token(
# Only save tokens if we are done prefilling for this request
batch.all_input_ids_tensor[
i,
batch.cache_lengths_tensor[i] + batch.input_lengths[i] : batch.cache_lengths_tensor[i]
batch.cache_lengths_tensor[i]
+ batch.input_lengths[i] : batch.cache_lengths_tensor[i]
+ batch.input_lengths[i]
+ accepted_ids[i],
] = next_input_ids[cu_accepted_ids[i] : cu_accepted_ids[i + 1]]
Expand Down
Loading