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/quantization/kernels/scaled_mm/cpu.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py
--- a/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py
+++ b/vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py
--- a/vllm/model_executor/layers/quantization/modelopt.py
+++ b/vllm/model_executor/layers/quantization/modelopt.py
--- a/vllm/model_executor/layers/quantization/moe_wna16.py
+++ b/vllm/model_executor/layers/quantization/moe_wna16.py
--- a/vllm/model_executor/layers/quantization/mxfp4.py
+++ b/vllm/model_executor/layers/quantization/mxfp4.py
--- a/vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
+++ b/vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
--- a/vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
--- a/vllm/model_executor/layers/quantization/utils/fp8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/fp8_utils.py
--- a/vllm/model_executor/layers/quantization/utils/mxfp4_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/mxfp4_utils.py
--- a/vllm/model_executor/layers/rotary_embedding/__init__.py
+++ b/vllm/model_executor/layers/rotary_embedding/__init__.py
--- a/vllm/model_executor/layers/rotary_embedding/base.py
+++ b/vllm/model_executor/layers/rotary_embedding/base.py
--- a/vllm/model_executor/layers/rotary_embedding/common.py
+++ b/vllm/model_executor/layers/rotary_embedding/common.py
--- a/vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py
+++ b/vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py
--- a/vllm/model_executor/layers/rotary_embedding/mrope.py
+++ b/vllm/model_executor/layers/rotary_embedding/mrope.py
--- a/vllm/model_executor/layers/rotary_embedding/xdrope.py
+++ b/vllm/model_executor/layers/rotary_embedding/xdrope.py
--- a/vllm/model_executor/models/adapters.py
+++ b/vllm/model_executor/models/adapters.py
--- a/vllm/model_executor/models/afmoe.py
+++ b/vllm/model_executor/models/afmoe.py
--- a/vllm/model_executor/models/apertus.py
+++ b/vllm/model_executor/models/apertus.py