[Bugfix][Quantization] Refresh online NVFP4 scales before reload post-processing (#57954)
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com> Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com> Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: aoshen02 <aoshen@inferact.ai>
This commit is contained in:
co-authored by
aoshen02
Claude Opus 5
aoshen02
parent
16070ed7e9
commit
3652f35e7c
@@ -178,6 +178,14 @@ class Nvfp4OnlineMoEMethod(OnlineMoEMethodBase):
|
||||
routing_tables=layer._expert_routing_tables(),
|
||||
per_token_activation=True,
|
||||
)
|
||||
else:
|
||||
# Reload creates new scale tensors; derived kernel scales must use
|
||||
# their new values before layerwise reload restores captured storage.
|
||||
assert self.moe_quant_config is not None
|
||||
assert self.moe_quant_config.g1_alphas is not None
|
||||
assert self.moe_quant_config.g2_alphas is not None
|
||||
self.moe_quant_config.g1_alphas.copy_(w13_scale_2)
|
||||
self.moe_quant_config.g2_alphas.copy_(w2_scale_2)
|
||||
|
||||
self.moe_kernel.fused_experts.process_weights_after_loading(layer)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user