Merge tag 'v0.15.0rc1' into v0.15.0rc1-dev

d76fc11e · zhuwenwen · 38166ec4 · 58996f35 · d76fc11e · d76fc11e
Commit d76fc11e authored Jan 28, 2026 by zhuwenwen
20 changed files
--- 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/moe_permute_unpermute.py
+++ b/vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py
--- a/vllm/model_executor/layers/fused_moe/mori_prepare_finalize.py
+++ b/vllm/model_executor/layers/fused_moe/mori_prepare_finalize.py
--- a/vllm/model_executor/layers/fused_moe/oracle/fp8.py
+++ b/vllm/model_executor/layers/fused_moe/oracle/fp8.py
--- a/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py
+++ b/vllm/model_executor/layers/fused_moe/oracle/nvfp4.py
--- a/vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py
+++ b/vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py
--- a/vllm/model_executor/layers/fused_moe/prepare_finalize.py
+++ b/vllm/model_executor/layers/fused_moe/prepare_finalize.py
--- a/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.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/mamba/mamba_mixer2.py
+++ b/vllm/model_executor/layers/mamba/mamba_mixer2.py
--- a/vllm/model_executor/layers/mamba/ops/mamba_ssm.py
+++ b/vllm/model_executor/layers/mamba/ops/mamba_ssm.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_w4a4_nvfp4.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/modelopt.py
+++ b/vllm/model_executor/layers/quantization/modelopt.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/quant_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/quant_utils.py