Skip to content
Open
Changes from all commits
Commits
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 vllm_spyre/v1/worker/spyre_model_runner.py
Original file line number Diff line number Diff line change
Expand Up @@ -999,7 +999,7 @@ def _make_kv_cache_manager(self) -> FullAttentionManager:
def _get_blocks(self, request_id: str) -> list[KVCacheBlock]:
return self.kv_cache_manager.req_to_blocks[request_id]

def get_total_spyre_blocks(self) -> int:
def get_total_spyre_blocks(self) -> int:
"""Returns the total number of KV cache blocks available for spyre.
This currently returns the number of blocks required for a full-sized
batch, which may be greater than the available memory.
Expand Down
Loading