liger-kernel-nightly 0.5.10.dev20250618073949__py3-none-any.whl → 0.5.10.dev20250618170631__py3-none-any.whl

liger_kernel/transformers/monkey_patch.py

@@ -1208,7 +1208,8 @@ def apply_liger_kernel_to_qwen3_moe(
             _patch_rms_norm_module(base_model.norm)
         for decoder_layer in base_model.layers:
             if swiglu:
-                _patch_swiglu_module(decoder_layer.mlp, LigerQwen3MoeSwiGLUMLP)
+                for mlp_expert in decoder_layer.mlp.experts:
+                    _patch_swiglu_module(mlp_expert, LigerQwen3MoeSwiGLUMLP)
             if rms_norm:
                 _patch_rms_norm_module(decoder_layer.input_layernorm)
                 _patch_rms_norm_module(decoder_layer.post_attention_layernorm)

{liger_kernel_nightly-0.5.10.dev20250618073949.dist-info → liger_kernel_nightly-0.5.10.dev20250618170631.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.5.10.dev20250618073949
+Version: 0.5.10.dev20250618170631
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 

{liger_kernel_nightly-0.5.10.dev20250618073949.dist-info → liger_kernel_nightly-0.5.10.dev20250618170631.dist-info}/RECORD

@@ -53,7 +53,7 @@ liger_kernel/transformers/grpo_loss.py,sha256=uAkUNKSnUGEOqa82L9w2e6AI1kcmG8K45-
 liger_kernel/transformers/jsd.py,sha256=DGqRnxIZxsvxo0_tbbxX3b-sDbDjC_yKufyRIHCcScY,2979
 liger_kernel/transformers/kl_div.py,sha256=WLffFbh1EExD2Eb1F7lN11fo9JJC-0751WJjZAF1Fj8,409
 liger_kernel/transformers/layer_norm.py,sha256=c9pk3PEasOKYR0rhe5e5nNrnYKVCEW4VC8S6LpCq9EQ,906
-liger_kernel/transformers/monkey_patch.py,sha256=IWqNiimHL0895yo0TjQ3lN_Y8fKGesxC-bF5He6zB2g,77536
+liger_kernel/transformers/monkey_patch.py,sha256=pB9qQPKfaA3MS-qtsOTG1YEAC6kRYyrsdk7JhMLrwSE,77594
 liger_kernel/transformers/multi_token_attention.py,sha256=l9VDICK0dfmifUDW668hGscP8AHq2rYcM2oGUa3baRQ,1751
 liger_kernel/transformers/qwen2vl_mrope.py,sha256=5EwSqrMdsL9MYspeBMXBsNJKvH0MOmRrtJXAJlnnlOI,1047
 liger_kernel/transformers/rms_norm.py,sha256=eErIr1n-13oVrc1VJY07lqazYelw_vlu9Az__RmXPSE,2717
@@ -87,9 +87,9 @@ liger_kernel/transformers/trainer/__init__.py,sha256=p7yQfklV8-467qSz_ZMimkbDF7H
 liger_kernel/transformers/trainer/orpo_trainer.py,sha256=tX0h63aOFe3rNqTmk6JpMf75UPo981yzEa6TghnjS0Q,5370
 liger_kernel/triton/__init__.py,sha256=qCiCamzCRv6lpV8IqpAc9YMdNKC7GKurClWceQPnlis,92
 liger_kernel/triton/monkey_patch.py,sha256=Rd0hUHAzDkFfHvnX7-PBaNK5EKnZhtfM_h-fgQH9HPY,1568
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/METADATA,sha256=cjOju93tisY2Oux3OO1HE8UM-PWHlP92vkWajAgQCwU,24358
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
-liger_kernel_nightly-0.5.10.dev20250618073949.dist-info/RECORD,,
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/METADATA,sha256=sxNO4_4HQ8OZ23Qx5TUIbXSHesEBgYfJGXM4qCOFn_8,24358
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
+liger_kernel_nightly-0.5.10.dev20250618170631.dist-info/RECORD,,