[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:
fxmarty-amd
2026-10-08 12:04:46 -04:00
committed by GitHub
co-authored by OpenAI Codex Misha Goin
parent e2414ec1db
commit 9f3d70e081
24 changed files with 984 additions and 73 deletions
+1
View File
@@ -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,