Skip to content

Commit

Permalink
[Lint] Adjust logging to be less than 80
Browse files Browse the repository at this point in the history
Signed-off-by: Ahmed Mansy <[email protected]>
  • Loading branch information
Ahmed14z committed Nov 4, 2024
1 parent c1dea49 commit 1d976f2
Showing 1 changed file with 2 additions and 1 deletion.
3 changes: 2 additions & 1 deletion vllm/worker/worker.py
Original file line number Diff line number Diff line change
Expand Up @@ -197,7 +197,7 @@ def determine_num_available_blocks(self) -> Tuple[int, int]:
num_cpu_blocks = max(num_cpu_blocks, 0)

logger.info(
"Using num_gpu_blocks_override=%d, calculated num_cpu_blocks=%d",
"Using num_gpu_blocks_override=%d,calculated num_cpu_blocks=%d",
num_gpu_blocks_override, num_cpu_blocks)

return num_gpu_blocks_override, num_cpu_blocks
Expand Down Expand Up @@ -271,6 +271,7 @@ def _assert_memory_footprint_increased_during_profiling(self):
f"Initial free memory {self.init_gpu_memory}, current free memory"
f" {free_gpu_memory}. This happens when the GPU memory was "
"not properly cleaned up before initializing the vLLM instance.")

def initialize_cache(self, num_gpu_blocks: int,
num_cpu_blocks: int) -> None:
"""Allocate GPU and CPU KV cache with the specified number of blocks.
Expand Down

0 comments on commit 1d976f2

Please sign in to comment.