Allow block size 256 (#121)

HabanaAI · Jul 24, 2024 · 067a243 · 067a243
1 parent 260c710
commit 067a243
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py
@@ -257,7 +257,7 @@ def add_cli_args(
         parser.add_argument('--block-size',
                             type=int,
                             default=EngineArgs.block_size,
-                            choices=[8, 16, 32, 64, 128],
+                            choices=[8, 16, 32, 64, 128, 256],
                             help='Token block size for contiguous chunks of '
                             'tokens.')