vllm/vllm/executor/utils.py

14 lines
722 B
Python

def check_block_size_valid(num_gpu_blocks, block_size, max_model_len) -> None:
if num_gpu_blocks <= 0:
raise ValueError("No available memory for the cache blocks. "
"Try increasing `gpu_memory_utilization` when "
"initializing the engine.")
max_seq_len = block_size * num_gpu_blocks
if max_model_len > max_seq_len:
raise ValueError(
f"The model's max seq len ({max_model_len}) "
"is larger than the maximum number of tokens that can be "
f"stored in KV cache ({max_seq_len}). Try increasing "
"`gpu_memory_utilization` or decreasing `max_model_len` when "
"initializing the engine.")