Merge tag 'v0.14.0' into v0.14.0-dev

7e63ef82 · zhuwenwen · 8cbcac5d · b17039bc · 7e63ef82 · 7e63ef82
Commit 7e63ef82 authored Jan 21, 2026 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=129,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=129,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=gfx938_64cu.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=gfx938_64cu.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=160,N=768,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=160,N=768,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
--- a/vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
--- a/vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=gfx928_120cu_nn.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=gfx928_120cu_nn.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
--- a/vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
--- a/vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=gfx928_120cu_nn.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=gfx928_120cu_nn.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=64,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=64,N=512,device_name=NVIDIA_B200,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/deep_gemm_moe.py
+++ b/vllm/model_executor/layers/fused_moe/deep_gemm_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/fallback.py
+++ b/vllm/model_executor/layers/fused_moe/fallback.py
--- a/vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py
+++ b/vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py