[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
@@ -162,6 +162,7 @@ def test_routed_experts_loads_per_expert_biases():
|
||||
class Loader:
|
||||
quant_config = None
|
||||
quant_method = object()
|
||||
_fused_shared_expert_quantizer = None
|
||||
moe_config = SimpleNamespace(
|
||||
is_act_and_mul=True,
|
||||
tp_rank=0,
|
||||
|
||||
Reference in New Issue
Block a user