Skip to content

[Bugfix] Fix assertion in NeuronExecutor #5841

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 1 commit into from
Jun 26, 2024
Merged

[Bugfix] Fix assertion in NeuronExecutor #5841

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 3 additions & 3 deletions vllm/executor/neuron_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,9 +48,9 @@ def initialize_cache(self, num_gpu_blocks: int,
def execute_model(
self,
execute_model_req: ExecuteModelRequest) -> List[SamplerOutput]:
assert (execute_model_req.blocks_to_swap_in == {}
and execute_model_req.blocks_to_swap_out == {}
and execute_model_req.blocks_to_copy == {}), (
assert (not execute_model_req.blocks_to_swap_in
and not execute_model_req.blocks_to_swap_out
and not execute_model_req.blocks_to_copy), (
"Cache operations are not supported for Neuron backend.")
assert execute_model_req.num_lookahead_slots == 0, (
"lookahead not supported for Neuron backend.")
Expand Down
Loading