MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-09-30 03:49:49 +01:00
parent d3bd171123
commit 61aedb5ffe
36 changed files with 964 additions and 905 deletions
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
@@ -43,7 +43,7 @@ logger = init_logger(__name__)


 def get_moe_quant_method(
-    config: QuantizationConfig,
+    config: "GPTQMarlinConfig",
    layer: torch.nn.Module,
    prefix: str,
    moe_method_cls: type,