[Bugfix] Fix block size validation (#10938)

vllm-project · Dec 16, 2024 · 69ba344 · 69ba344
1 parent da6f409
commit 69ba344
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py
@@ -425,7 +425,7 @@ def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
         parser.add_argument('--block-size',
                             type=int,
                             default=EngineArgs.block_size,
-                            choices=[8, 16, 32, 64, 128],
+                            choices=[8, 16, 32],
                             help='Token block size for contiguous chunks of '
                             'tokens. This is ignored on neuron devices and '
                             'set to max-model-len')