[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
+1 -2
View File
@@ -16,14 +16,13 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
"bias) -> ()");
m.impl("topk_sigmoid", torch::kCUDA, &topk_sigmoid);
#ifndef USE_ROCM
m.def(
"topk_softplus_sqrt(Tensor! topk_weights, Tensor! topk_indices, Tensor! "
"token_expert_indices, Tensor gating_output, bool renormalize, float "
"routed_scaling_factor, Tensor? "
"bias, Tensor? input_ids, Tensor? tid2eid) -> ()");
m.impl("topk_softplus_sqrt", torch::kCUDA, &topk_softplus_sqrt);
#endif
// Calculate the result of moe by summing up the partial results
// from all selected experts.
m.def("moe_sum(Tensor input, Tensor! output) -> ()");