Skip to content

AICSDEV-216: gaudi oss enablement #192

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

AICSDEV-216: gaudi oss enablement #192

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
ed4354e
AICSDEV-216: gaudi oss enablement
vermavis Sep 9, 2025
40c3e87
Merge branch 'vllm-project:main' into AICSDEV-216
vermavis Sep 23, 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
2 changes: 2 additions & 0 deletions vllm_gaudi/attention/backends/hpu_attn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -381,8 +381,10 @@ def __init__(
attn_type: str = AttentionType.DECODER,
kv_sharing_target_layer_name: Optional[str] = None,
use_irope: bool = False,
sinks: Optional[int] = None,
) -> None:
super(AttentionImpl, self).__init__()
self._sinks = sinks
if kv_sharing_target_layer_name is not None:
raise NotImplementedError("KV sharing is not currently supported on HPU.")
if use_irope:
Expand Down
2 changes: 1 addition & 1 deletion vllm_gaudi/extension/ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -474,7 +474,7 @@ def forward(self, hidden_states, expert_routing_table, router_weights, permuted_
w12=w1_list,
w3=w2_list,
permuted_weights=permuted_weights,
activation=activation,
activation="silu",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If silu is necessary, pass through config instead of hard-code

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks like upstream vllm has this hardcoded to: swigluoai.
https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/models/gpt_oss.py#L158

experts_min=self.experts_min,
experts_max=self.experts_max)
for i in range(self.moe_n_slice):
Expand Down