liger-kernel-nightly 0.6.0.dev20250708194445__py3-none-any.whl → 0.6.0.dev20250709042125__py3-none-any.whl

liger_kernel/transformers/monkey_patch.py

@@ -537,7 +537,10 @@ def apply_liger_kernel_to_mllama(
         if isinstance(model, MllamaForConditionalGeneration):
             language_model: MllamaForCausalLM = model.language_model
             vision_model: MllamaVisionModel = model.vision_model
-            text_model: MllamaTextModel = language_model
+            if isinstance(language_model, MllamaForCausalLM):
+                text_model: MllamaTextModel = language_model.model
+            else:
+                text_model = language_model
         elif isinstance(model, MllamaForCausalLM):
             text_model = model.model
             vision_model = None
@@ -1096,7 +1099,9 @@ def apply_liger_kernel_to_paligemma(
     # PaliGemma submodules are ['vision_tower', 'multi_modal_projector', 'language_model']
 
     from transformers.models.gemma.modeling_gemma import GemmaForCausalLM
+    from transformers.models.gemma.modeling_gemma import GemmaModel
     from transformers.models.gemma2.modeling_gemma2 import Gemma2ForCausalLM
+    from transformers.models.gemma2.modeling_gemma2 import Gemma2Model
     from transformers.models.paligemma import modeling_paligemma
     from transformers.models.paligemma.modeling_paligemma import PaliGemmaForConditionalGeneration
     from transformers.models.siglip import modeling_siglip
@@ -1155,7 +1160,7 @@ def apply_liger_kernel_to_paligemma(
 
         language_model = model.language_model
 
-        if isinstance(language_model, GemmaForCausalLM):
+        if isinstance(language_model, (GemmaForCausalLM, GemmaModel)):
             apply_liger_kernel_to_gemma(
                 rope=rope,
                 cross_entropy=False,
@@ -1165,7 +1170,7 @@ def apply_liger_kernel_to_paligemma(
                 model=language_model,
             )
 
-        elif isinstance(language_model, Gemma2ForCausalLM):
+        elif isinstance(language_model, (Gemma2ForCausalLM, Gemma2Model)):
             apply_liger_kernel_to_gemma2(
                 rope=rope,
                 cross_entropy=False,

{liger_kernel_nightly-0.6.0.dev20250708194445.dist-info → liger_kernel_nightly-0.6.0.dev20250709042125.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.6.0.dev20250708194445
+Version: 0.6.0.dev20250709042125
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 
@@ -33,7 +33,7 @@ License-File: NOTICE
 Requires-Dist: torch>=2.1.2
 Requires-Dist: triton>=2.3.1
 Provides-Extra: dev
-Requires-Dist: transformers>=4.44.2; extra == "dev"
+Requires-Dist: transformers>=4.49.0; extra == "dev"
 Requires-Dist: matplotlib>=3.7.2; extra == "dev"
 Requires-Dist: flake8>=4.0.1.1; extra == "dev"
 Requires-Dist: black>=24.4.2; extra == "dev"

{liger_kernel_nightly-0.6.0.dev20250708194445.dist-info → liger_kernel_nightly-0.6.0.dev20250709042125.dist-info}/RECORD

@@ -54,7 +54,7 @@ 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=rXmaVry8hdpnH8HunfJhZmrsdlwAxjMP3x10ZYMnTy4,85554
+liger_kernel/transformers/monkey_patch.py,sha256=W7KgJN-rrLZS3pRZ5debO_dSN7zddPegKjqOIP39wR0,85856
 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=vkekcvTeWY8vL4H6hg3t0XeY0Ew_3OFMPHuzqlxPPVw,2719
@@ -89,9 +89,9 @@ 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-0.6.0.dev20250708194445.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
-liger_kernel_nightly-0.6.0.dev20250708194445.dist-info/METADATA,sha256=kV3blHZ_pcaJBcRKdgCg2T6EOvzFL3NwMoDcipaSdc0,24535
-liger_kernel_nightly-0.6.0.dev20250708194445.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
-liger_kernel_nightly-0.6.0.dev20250708194445.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-liger_kernel_nightly-0.6.0.dev20250708194445.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
-liger_kernel_nightly-0.6.0.dev20250708194445.dist-info/RECORD,,
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/METADATA,sha256=wPo1-0a5kmFfk7NvN28x3Sk_NV0g4AEzrOnbB4fJHMk,24535
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
+liger_kernel_nightly-0.6.0.dev20250709042125.dist-info/RECORD,,