[Bug] Fix the OOM condition for CPU cache (#260)

2023-06-26 11:16:13 -07:00
parent 471a7a4566
commit 0b7db411b5
2 changed files with 3 additions and 1 deletions
--- a/vllm/engine/llm_engine.py
+++ b/vllm/engine/llm_engine.py
@@ -128,7 +128,7 @@ class LLMEngine:
        logger.info(f'# GPU blocks: {num_gpu_blocks}, '
                    f'# CPU blocks: {num_cpu_blocks}')

-        if num_gpu_blocks <= 0 or num_cpu_blocks <= 0:
+        if num_gpu_blocks <= 0:
            raise ValueError("No available memory for the cache blocks. "
                             "Try increasing `gpu_memory_utilization` when "
                             "initializing the engine.")