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

[Bugfix][TPU] Add prompt adapter methods to TPUExecutor #6279

Merged
merged 1 commit into from
Jul 10, 2024
Merged

[Bugfix][TPU] Add prompt adapter methods to TPUExecutor #6279

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
31 changes: 25 additions & 6 deletions vllm/executor/tpu_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,8 +81,7 @@ def initialize_cache(

def determine_num_available_blocks(self) -> Tuple[int, int]:
"""Determine the number of available KV blocks by invoking the
underlying worker.
"""
underlying worker."""
return self.driver_worker.determine_num_available_blocks()

def execute_model(
Expand All @@ -93,16 +92,36 @@ def execute_model(
return output

def add_lora(self, lora_request: LoRARequest) -> bool:
raise NotImplementedError("LoRA is not implemented for TPU backend.")
raise NotImplementedError(
"LoRA is currently not supported by the TPU backend.")

def remove_lora(self, lora_id: int) -> bool:
raise NotImplementedError("LoRA is not implemented for TPU backend.")
raise NotImplementedError(
"LoRA is currently not supported by the TPU backend.")

def pin_lora(self, lora_id: int) -> bool:
raise NotImplementedError("LoRA is not implemented for TPU backend.")
raise NotImplementedError(
"LoRA is currently not supported by the TPU backend.")

def list_loras(self) -> Set[int]:
raise NotImplementedError("LoRA is not implemented for TPU backend.")
raise NotImplementedError(
"LoRA is currently not supported by the TPU backend.")

def add_prompt_adapter(self, prompt_adapter_request) -> bool:
raise NotImplementedError(
"Soft prompt is currently not supported by the TPU backend.")

def remove_prompt_adapter(self, prompt_adapter_id: int) -> bool:
raise NotImplementedError(
"Soft prompt is currently not supported by the TPU backend.")

def pin_prompt_adapter(self, prompt_adapter_id: int) -> bool:
raise NotImplementedError(
"Soft prompt is currently not supported by the TPU backend.")

def list_prompt_adapters(self) -> Set[int]:
raise NotImplementedError(
"Soft prompt is currently not supported by the TPU backend.")

def check_health(self) -> None:
# TPUExecutor will always be healthy as long as it's running.
Expand Down
Loading