Various cosmetic/comment fixes (#12089)

Signed-off-by: mgoin <michael@neuralmagic.com>
2025-01-16 04:59:06 -05:00
parent f8ef146f03
commit 9aa1519f08
14 changed files with 16 additions and 29 deletions
--- a/vllm/model_executor/models/qwen2.py
+++ b/vllm/model_executor/models/qwen2.py
@@ -367,8 +367,7 @@ class Qwen2Model(nn.Module):
                continue
            if (self.quant_config is not None and
                (scale_name := self.quant_config.get_cache_scale(name))):
-                # Loading kv cache scales for quark and
-                # compressed-tensors quantization
+                # Loading kv cache quantization scales
                param = params_dict[scale_name]
                weight_loader = getattr(param, "weight_loader",
                                        default_weight_loader)