Merge tag 'v0.14.0rc0' into v0.14.0rc0-ori

a810671a · zhuwenwen · 86b5aefe · 6a09612b · a810671a · a810671a
Commit a810671a authored Jan 08, 2026 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/fused_moe/__init__.py
+++ b/vllm/model_executor/layers/fused_moe/__init__.py
--- a/vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
--- 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=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=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=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=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/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
--- a/vllm/model_executor/layers/fused_moe/fused_moe_method_base.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe_method_base.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/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py