From c66baf3199f7588a27a369879b7244c972b1eea3 Mon Sep 17 00:00:00 2001 From: MOVZX Date: Sun, 18 Oct 2026 23:17:51 +0700 Subject: [PATCH] [BugFix] Only probe quantization overrides that exist in the tree The SM86 cut removed the inc and deepseek_v4_fp8 loaders but ModelConfig still probed them, crashing compressed-tensors checkpoints with "Invalid quantization method: inc". Filter the override probe list to the supported methods. Co-authored-by: Hinata --- vllm/config/model.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/vllm/config/model.py b/vllm/config/model.py index 796e599bcc..77bed01f7f 100644 --- a/vllm/config/model.py +++ b/vllm/config/model.py @@ -1392,7 +1392,9 @@ class ModelConfig: # Any custom overrides will be in quantization_methods so we place # them at the start of the list so custom overrides have preference # over the built-in ones. - quantization_methods = quantization_methods + overrides + quantization_methods = quantization_methods + [ + o for o in overrides if o in supported_quantization + ] # Detect which checkpoint is it for name in quantization_methods: