Merge tag 'v0.18.1rc0' into v0.18.1rc0-ori

0da93439 · zhuwenwen · 25f2f756 · 298e5108 · 0da93439 · 0da93439
Commit 0da93439 authored Mar 26, 2026 by zhuwenwen
20 changed files
--- a/vllm/model_executor/kernels/linear/mixed_precision/__init__.py
+++ b/vllm/model_executor/kernels/linear/mixed_precision/__init__.py
--- a/vllm/model_executor/kernels/linear/mixed_precision/conch.py
+++ b/vllm/model_executor/kernels/linear/mixed_precision/conch.py
--- a/vllm/model_executor/kernels/linear/mixed_precision/cpu.py
+++ b/vllm/model_executor/kernels/linear/mixed_precision/cpu.py
--- a/vllm/model_executor/kernels/linear/mixed_precision/exllama.py
+++ b/vllm/model_executor/kernels/linear/mixed_precision/exllama.py
--- a/vllm/model_executor/kernels/linear/mixed_precision/xpu.py
+++ b/vllm/model_executor/kernels/linear/mixed_precision/xpu.py
--- a/vllm/model_executor/layers/attention/attention.py
+++ b/vllm/model_executor/layers/attention/attention.py
--- a/vllm/model_executor/layers/attention/mla_attention.py
+++ b/vllm/model_executor/layers/attention/mla_attention.py
--- a/vllm/model_executor/layers/attention/mm_encoder_attention.py
+++ b/vllm/model_executor/layers/attention/mm_encoder_attention.py
--- a/vllm/model_executor/layers/attention/static_sink_attention.py
+++ b/vllm/model_executor/layers/attention/static_sink_attention.py
--- a/vllm/model_executor/layers/fused_moe/all2all_utils.py
+++ b/vllm/model_executor/layers/fused_moe/all2all_utils.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/configs/E=256,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
--- a/vllm/model_executor/layers/fused_moe/cpu_fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/cpu_fused_moe.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/deepep_ll_prepare_finalize.py
+++ b/vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py
--- a/vllm/model_executor/layers/fused_moe/experts/trtllm_fp8_moe.py
+++ b/vllm/model_executor/layers/fused_moe/experts/trtllm_fp8_moe.py
--- a/vllm/model_executor/layers/fused_moe/trtllm_moe.py
+++ b/vllm/model_executor/layers/fused_moe/trtllm_moe.py
--- a/vllm/model_executor/layers/fused_moe/fused_batched_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_batched_moe.py
--- a/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_marlin_moe.py
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py