liger-kernel-nightly 0.5.5.dev20250327235249__py3-none-any.whl → 0.5.5.dev20250328142430__py3-none-any.whl

liger_kernel/chunked_loss/fused_linear_distillation.py

@@ -112,6 +112,9 @@ class LigerFusedLinearDistillationBase(torch.autograd.Function):
             compute_ce_loss=compute_ce_loss,
         )
 
+        student_logits_chunk /= temperature
+        teacher_logits_chunk /= temperature
+
         # If the teacher and student token size is different, pad student logits to match the teacher's.
         # This only applies to cases where they share exactly the same vocab and tokenizer just
         # that teacher logit is padded for some training efficiency such as
@@ -123,13 +126,10 @@ class LigerFusedLinearDistillationBase(torch.autograd.Function):
             pad_tensor = torch.zeros(
                 (*student_logits_chunk.shape[:-1], pad_size),
                 dtype=student_logits_chunk.dtype,
-                device=student_logits_chunk.device
+                device=student_logits_chunk.device,
             )
             student_logits_chunk = torch.cat([student_logits_chunk, pad_tensor], dim=-1)
 
-        student_logits_chunk /= temperature
-        teacher_logits_chunk /= temperature
-
         hard_loss /= full_target.shape[0]
 
         soft_loss = distillation_loss_fn(student_logits_chunk, teacher_logits_chunk, **loss_kwargs)

{liger_kernel_nightly-0.5.5.dev20250327235249.dist-info → liger_kernel_nightly-0.5.5.dev20250328142430.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.5.5.dev20250327235249
+Version: 0.5.5.dev20250328142430
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 

{liger_kernel_nightly-0.5.5.dev20250327235249.dist-info → liger_kernel_nightly-0.5.5.dev20250328142430.dist-info}/RECORD

@@ -6,7 +6,7 @@ liger_kernel/chunked_loss/__init__.py,sha256=ATu-xX5Fc49Cr6yBOGBRNTo593ZrU5ZCsIu
 liger_kernel/chunked_loss/cpo_loss.py,sha256=Gzz1eU4kgcbdubFVRy55e8A1Cr-r45UgNicXwZIjmBU,5454
 liger_kernel/chunked_loss/dpo_loss.py,sha256=xZwGqS04si9zXyob95SAdalC-hajZg8fWINqiqffN8k,5855
 liger_kernel/chunked_loss/functional.py,sha256=THWWpCnRVhTVfnPnyvQjdBvo1JDtxhwLmtZE_yiBBqM,817
-liger_kernel/chunked_loss/fused_linear_distillation.py,sha256=y7e2mF_6HGMNNuoWAmJ8Y5bK-hRUe2q4-R6r7lf-Mw8,11934
+liger_kernel/chunked_loss/fused_linear_distillation.py,sha256=ooR-qnZCyWJN935oHCSWLaKKKyaYERyhNczRGi1VOiw,11935
 liger_kernel/chunked_loss/fused_linear_preference.py,sha256=ojB42jYPu0c4ki96Ft-hy7Sf6fh_WikG-aWNrlZzSio,18362
 liger_kernel/chunked_loss/fused_linear_rlhf.py,sha256=wGujqwLz91mOE9MmdenhBIKvbmswhwtINMCpcP7D74c,9050
 liger_kernel/chunked_loss/fused_linear_unpaired_preference.py,sha256=RiuK3UtRwH9T6jZ36sA8Urj-TVuOLOO2syLg_JOQapY,13437
@@ -71,9 +71,9 @@ liger_kernel/transformers/trainer/__init__.py,sha256=p7yQfklV8-467qSz_ZMimkbDF7H
 liger_kernel/transformers/trainer/orpo_trainer.py,sha256=pdekW7l6Qg_aqa5SYKYlSWUF8m3lkOFvFLcIMEHrz9s,8338
 liger_kernel/triton/__init__.py,sha256=qCiCamzCRv6lpV8IqpAc9YMdNKC7GKurClWceQPnlis,92
 liger_kernel/triton/monkey_patch.py,sha256=Rd0hUHAzDkFfHvnX7-PBaNK5EKnZhtfM_h-fgQH9HPY,1568
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/METADATA,sha256=4_bQ76AZvAHUe6dzZt_JTtxjAX7_UV6O5zLmi7RNmK4,22959
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
-liger_kernel_nightly-0.5.5.dev20250327235249.dist-info/RECORD,,
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/METADATA,sha256=ZCqBj_JT8pEfnanXMGvgjo_IGq-mLd3Ii199ohgolVc,22959
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/WHEEL,sha256=iAkIy5fosb7FzIOwONchHf19Qu7_1wCWyFNR5gu9nU0,91
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
+liger_kernel_nightly-0.5.5.dev20250328142430.dist-info/RECORD,,