[ROCm][Bugfix] Ensure that the moe_wna16_gemm kernel is not built on ROCm platforms. (#14629)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
+2
-1
@@ -18,7 +18,7 @@ void sgl_moe_align_block_size(torch::Tensor topk_ids, int64_t num_experts,
|
||||
torch::Tensor sorted_token_ids,
|
||||
torch::Tensor experts_ids,
|
||||
torch::Tensor num_tokens_post_pad);
|
||||
|
||||
#ifndef USE_ROCM
|
||||
torch::Tensor moe_wna16_gemm(torch::Tensor input, torch::Tensor output,
|
||||
torch::Tensor b_qweight, torch::Tensor b_scales,
|
||||
std::optional<torch::Tensor> b_qzeros,
|
||||
@@ -28,3 +28,4 @@ torch::Tensor moe_wna16_gemm(torch::Tensor input, torch::Tensor output,
|
||||
torch::Tensor num_tokens_post_pad, int64_t top_k,
|
||||
int64_t BLOCK_SIZE_M, int64_t BLOCK_SIZE_N,
|
||||
int64_t BLOCK_SIZE_K, int64_t bit);
|
||||
#endif
|
||||
@@ -31,6 +31,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
|
||||
" Tensor! num_tokens_post_pad) -> ()");
|
||||
m.impl("sgl_moe_align_block_size", torch::kCUDA, &sgl_moe_align_block_size);
|
||||
|
||||
#ifndef USE_ROCM
|
||||
m.def(
|
||||
"moe_wna16_gemm(Tensor input, Tensor! output, Tensor b_qweight, "
|
||||
"Tensor b_scales, Tensor? b_qzeros, "
|
||||
@@ -41,7 +42,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
|
||||
|
||||
m.impl("moe_wna16_gemm", torch::kCUDA, &moe_wna16_gemm);
|
||||
|
||||
#ifndef USE_ROCM
|
||||
m.def(
|
||||
"marlin_gemm_moe(Tensor! a, Tensor! b_q_weights, Tensor! sorted_ids, "
|
||||
"Tensor! topk_weights, Tensor! topk_ids, Tensor! b_scales, Tensor! "
|
||||
|
||||
Reference in New Issue
Block a user