Merge tag 'v0.13.0rc2' into v0.13.0rc2-ori

a3f8d5dd · zhuwenwen · 8d75f22e · f34eca5f · a3f8d5dd · a3f8d5dd
Commit a3f8d5dd authored Dec 17, 2025 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/batch_invariant.py
+++ b/vllm/model_executor/layers/batch_invariant.py
--- a/vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py
+++ b/vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py
--- a/vllm/model_executor/layers/fused_moe/config.py
+++ b/vllm/model_executor/layers/fused_moe/config.py
--- a/vllm/model_executor/layers/fused_moe/cutlass_moe.py
+++ b/vllm/model_executor/layers/fused_moe/cutlass_moe.py
--- a/vllm/model_executor/layers/fused_moe/deep_gemm_moe.py
+++ b/vllm/model_executor/layers/fused_moe/deep_gemm_moe.py
--- a/vllm/model_executor/layers/fused_moe/deep_gemm_utils.py
+++ b/vllm/model_executor/layers/fused_moe/deep_gemm_utils.py
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
--- a/vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py
--- a/vllm/model_executor/layers/fused_moe/layer.py
+++ b/vllm/model_executor/layers/fused_moe/layer.py
--- a/vllm/model_executor/layers/fused_moe/modular_kernel.py
+++ b/vllm/model_executor/layers/fused_moe/modular_kernel.py
--- a/vllm/model_executor/layers/fused_moe/shared_fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/shared_fused_moe.py
--- a/vllm/model_executor/layers/quantization/awq_marlin.py
+++ b/vllm/model_executor/layers/quantization/awq_marlin.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/gguf.py
+++ b/vllm/model_executor/layers/quantization/gguf.py
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py