Remove more unnecessary load_weights methods (#47058)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-06-30 15:22:16 +01:00
committed by GitHub
parent 0fc2512094
commit 1ab9522935
63 changed files with 1024 additions and 3774 deletions
@@ -567,12 +567,6 @@ class BitsAndBytesModelLoader(BaseModelLoader):
if is_moe_model(model):
self.expert_params_mapping = get_moe_expert_mapping(model)
if not self.expert_params_mapping:
raise AttributeError(
f"MoE Model {type(model).__name__} does not support "
"BitsAndBytes quantization yet. Ensure this model has "
"'get_expert_mapping' method."
)
# For some models like Molmo, we need to use hf_to_vllm_mapper
# to ensure correct loading of weights.
if hf_to_vllm_mapper := getattr(model, "hf_to_vllm_mapper", None):