From e1ba23566891e58c3a27a62663a3095b40cb3d69 Mon Sep 17 00:00:00 2001 From: Morrison Turnansky Date: Wed, 8 Oct 2025 16:04:12 -0400 Subject: [PATCH] [BugFix] Fix failing test quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled (#26436) Signed-off-by: morrison-turnansky --- vllm/config/vllm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/config/vllm.py b/vllm/config/vllm.py index 37b8c3fe6..f6e46bb27 100644 --- a/vllm/config/vllm.py +++ b/vllm/config/vllm.py @@ -597,7 +597,7 @@ class VllmConfig: # https://github.com/vllm-project/vllm/issues/25094 if has_blocked_weights(): custom_ops = self.compilation_config.custom_ops - if "none" not in custom_ops and "-quant_fp8" not in custom_ops: + if "-quant_fp8" not in custom_ops: custom_ops.append("+quant_fp8") def update_sizes_for_sequence_parallelism(self, possible_sizes: list) -> list: