biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046)

Browse Source
This commit is contained in:
Kyle Sayers
2025-07-01 06:20:34 -04:00
committed by GitHub
parent c05596f1a3
commit 9025a9a705
17 changed files with 107 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/model_executor/utils.py
View File

@@ -58,7 +58,8 @@ def _make_synced_weight_loader(original_weight_loader):
def get_packed_modules_mapping(model: torch.nn.Module) -> dict[str, list[str]]:
parent_map = copy.deepcopy(getattr(model, "packed_modules_mapping", {}))
parent_map = getattr(model, "packed_modules_mapping", None)
parent_map = copy.deepcopy(parent_map) if parent_map is not None else {}
# don't infer mapping if the model has defined it explicitly.
if parent_map:
@@ -66,7 +67,9 @@ def get_packed_modules_mapping(model: torch.nn.Module) -> dict[str, list[str]]:
# We only check main components instead of whole model submodules
for child in model.children():
child_map = getattr(child, "packed_modules_mapping", {})
child_map = getattr(child, "packed_modules_mapping", None)
child_map = copy.deepcopy(child_map) if child_map is not None else {}
if any((k in parent_map and parent_map[k] != v)
for k, v in child_map.items()):
raise ValueError(