liger-kernel-nightly 0.5.8.dev20250425182211__tar.gz → 0.5.8.dev20250428050809__tar.gz

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.5.8.dev20250425182211
+Version: 0.5.8.dev20250428050809
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "liger_kernel_nightly"
-version = "0.5.8.dev20250425182211"
+version = "0.5.8.dev20250428050809"
 description = "Efficient Triton kernels for LLM Training"
 urls = { "Homepage" = "https://github.com/linkedin/Liger-Kernel" }
 readme = { file = "README.md", content-type = "text/markdown" }

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/src/liger_kernel_nightly.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.5.8.dev20250425182211
+Version: 0.5.8.dev20250428050809
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/test/convergence/bf16/test_mini_models_multimodal.py

@@ -770,7 +770,6 @@ def run_mini_model_multimodal(
                     not QWEN2_VL_AVAILABLE,
                     reason="Qwen2-VL not available in this version of transformers",
                 ),
-                pytest.mark.skipif(device == "xpu", reason="skip for XPU"),
             ],
         ),
         pytest.param(
@@ -809,7 +808,6 @@ def run_mini_model_multimodal(
                     not QWEN2_5_VL_AVAILABLE,
                     reason="Qwen2.5-VL not available in this version of transformers",
                 ),
-                pytest.mark.skipif(device == "xpu", reason="skip for XPU"),
             ],
         ),
         pytest.param(

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/test/convergence/fp32/test_mini_models_multimodal.py

@@ -765,7 +765,6 @@ def run_mini_model_multimodal(
                     not QWEN2_VL_AVAILABLE,
                     reason="Qwen2-VL not available in this version of transformers",
                 ),
-                pytest.mark.skipif(device == "xpu", reason="skip for XPU"),
             ],
         ),
         pytest.param(
@@ -800,7 +799,6 @@ def run_mini_model_multimodal(
                     not QWEN2_5_VL_AVAILABLE,
                     reason="Qwen2.5-VL not available in this version of transformers",
                 ),
-                pytest.mark.skipif(device == "xpu", reason="skip for XPU"),
             ],
         ),
         pytest.param(

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/test/transformers/test_fused_linear_cross_entropy.py

@@ -105,7 +105,7 @@ class LigerLMHeadCE(torch.nn.Module):
 @pytest.mark.parametrize(
     "B, T, H, V",
     [
-        pytest.param(8, 128, 1024, 4096, marks=pytest.mark.skipif(device="xpu", reason="skip for XPU")),
+        (8, 128, 1024, 4096),
         (4, 47, 31, 123),  # random shape
     ],
 )
@@ -287,7 +287,7 @@ def test_correctness_functional(B, T, H, V, scalar, dtype, bias, ce_weight, atol
 @pytest.mark.parametrize(
     "B, T, H, V",
     [
-        pytest.param(8, 128, 1024, 4096, marks=pytest.mark.skipif(device="xpu", reason="skip for XPU")),
+        (8, 128, 1024, 4096),
         (4, 47, 31, 123),  # random shape
     ],
 )

{liger_kernel_nightly-0.5.8.dev20250425182211 → liger_kernel_nightly-0.5.8.dev20250428050809}/test/transformers/test_rms_norm.py

@@ -103,7 +103,7 @@ class GemmaRMSNorm(nn.Module):
     [
         (LlamaRMSNorm, 0.0, "llama"),
         (GemmaRMSNorm, 1.0, "gemma"),
-        pytest.param(BaseRMSNorm, 0.0, "none", marks=pytest.mark.skipif(device="xpu", reason="skip for XPU")),
+        (BaseRMSNorm, 0.0, "none"),
     ],
 )
 @pytest.mark.parametrize(