[Fix] Better error message when there is OOM during cache initialization (#203)

2023-06-22 15:30:06 +08:00
parent 14f0b39cda
commit 1d24ccb96c
2 changed files with 7 additions and 0 deletions
--- a/vllm/engine/llm_engine.py
+++ b/vllm/engine/llm_engine.py
@@ -127,6 +127,12 @@ class LLMEngine:
        # FIXME(woosuk): Change to debug log.
        logger.info(f'# GPU blocks: {num_gpu_blocks}, '
                    f'# CPU blocks: {num_cpu_blocks}')
+
+        if num_gpu_blocks <= 0 or num_cpu_blocks <= 0:
+            raise ValueError("No available memory for the cache blocks. "
+                             "Try increasing `gpu_memory_utilization` when "
+                             "initializing the engine.")
+
        self.cache_config.num_gpu_blocks = num_gpu_blocks
        self.cache_config.num_cpu_blocks = num_cpu_blocks