[Bugfix] Propagate quant_config to LFM2 ShortConv projections (#48917)

Signed-off-by: Alex Yuan <alex.yuan@liquid.ai>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Alex Yuan
2026-07-21 06:51:55 +00:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 616c9bd0f4
commit 8def3cdde2
3 changed files with 6 additions and 0 deletions
+1
View File
@@ -257,6 +257,7 @@ class Lfm2ShortConvDecoderLayer(nn.Module):
layer_idx=layer_idx,
model_config=model_config,
cache_config=cache_config,
quant_config=quant_config,
prefix=f"{prefix}.conv",
)
+1
View File
@@ -351,6 +351,7 @@ class Lfm2MoeShortConvDecoderLayer(nn.Module):
layer_idx=layer_idx,
model_config=model_config,
cache_config=cache_config,
quant_config=quant_config,
prefix=f"{prefix}.conv",
)