[New Model][ROCm] Add AMD support for DeepSeek V4 (#40871)

Signed-off-by: ganyi <ygan@amd.com>
Signed-off-by: whx-sjtu <xiaowang990929@gmail.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: ganyi <ygan@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
Hexiang Wang
2026-05-05 08:55:37 -07:00
committed by GitHub
co-authored by ganyi tjtanaa tjtanaavllm
parent 2228fe6868
commit 628c436301
22 changed files with 939 additions and 134 deletions
+6 -6
View File
@@ -307,12 +307,12 @@ set(VLLM_EXT_SRC
"csrc/quantization/activation_kernels.cu"
"csrc/cuda_utils_kernels.cu"
"csrc/custom_all_reduce.cu"
"csrc/torch_bindings.cpp")
"csrc/torch_bindings.cpp"
"csrc/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu")
if(VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_EXT_SRC
"csrc/minimax_reduce_rms_kernel.cu"
"csrc/fused_deepseek_v4_qnorm_rope_kv_insert_kernel.cu")
"csrc/minimax_reduce_rms_kernel.cu")
SET(CUTLASS_ENABLE_HEADERS_ONLY ON CACHE BOOL "Enable only the header library")
@@ -1047,13 +1047,13 @@ endif()
set(VLLM_MOE_EXT_SRC
"csrc/moe/torch_bindings.cpp"
"csrc/moe/moe_align_sum_kernels.cu"
"csrc/moe/topk_softmax_kernels.cu")
"csrc/moe/topk_softmax_kernels.cu"
"csrc/moe/topk_softplus_sqrt_kernels.cu")
if(VLLM_GPU_LANG STREQUAL "CUDA")
list(APPEND VLLM_MOE_EXT_SRC
"csrc/moe/moe_wna16.cu"
"csrc/moe/grouped_topk_kernels.cu"
"csrc/moe/topk_softplus_sqrt_kernels.cu")
"csrc/moe/grouped_topk_kernels.cu")
endif()
if(VLLM_GPU_LANG STREQUAL "CUDA")