Skip to content

Granite4 Quantization Bug Fix #28398

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
+2 −2
Open

Granite4 Quantization Bug Fix #28398

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0d11efc
Granite4 Add Quant Config
krishnateja95 Nov 10, 2025
375c61e
import re
krishnateja95 Nov 10, 2025
38a677b
minor indentation fix
krishnateja95 Nov 10, 2025
c7f5534
Fix Granite4 MoE weight loading function
krishnateja95 Nov 13, 2025
0c5b1ce
remove import re
krishnateja95 Nov 13, 2025
e0cb248
minor fix
krishnateja95 Nov 17, 2025
4825e50
Update weight loading
krishnateja95 Dec 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm/model_executor/models/granitemoehybrid.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,6 @@
maybe_prefix,
)


class GraniteMoeHybridMambaDecoderLayer(nn.Module):
def __init__(
self,
Expand Down Expand Up @@ -81,7 +80,7 @@ def __init__(
model_config=model_config,
cache_config=cache_config,
quant_config=quant_config,
prefix=f"{prefix}.mixer",
prefix=f"{prefix}.mamba",
)

self.block_sparse_moe = None
Expand Down Expand Up @@ -570,6 +569,7 @@ def _load_quant_expert(name, loaded_weight):
shard_id="w2",
expert_id=e,
)

elif n.endswith(".block_sparse_moe.router.layer.weight"):
gate_name = n.replace(
".block_sparse_moe.router.layer.weight",
Expand Down
Loading