[Quantization] Enable shared expert fusion compatibility with online shared_expert quantization (showcase: along Quark MXFP4 routed experts) (#55686)
Signed-off-by: Felix Marty <Felix.Marty@amd.com> Signed-off-by: fxmarty-amd <felmarty@amd.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: Misha Goin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
OpenAI Codex
Misha Goin
parent
e2414ec1db
commit
9f3d70e081
@@ -528,6 +528,7 @@ def test_padded_moe_reload_releases_each_layer(
|
||||
layer.quant_method = method
|
||||
layer.expert_map_manager = SimpleNamespace(map_global_to_local=lambda i: i)
|
||||
layer._loaded_expert_biases = set()
|
||||
layer._fused_shared_expert_quantizer = None
|
||||
method.create_weights(
|
||||
layer,
|
||||
experts,
|
||||
|
||||
Reference in New Issue
Block a user