[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:
@@ -1146,6 +1146,10 @@ def moe_wna16_gemm(input: torch.Tensor, output: torch.Tensor,
|
||||
num_tokens_post_pad: torch.Tensor, top_k: int,
|
||||
BLOCK_SIZE_M: int, BLOCK_SIZE_N: int, BLOCK_SIZE_K: int,
|
||||
bit: int) -> torch.Tensor:
|
||||
if not current_platform.is_cuda():
|
||||
raise NotImplementedError(
|
||||
"The optimized moe_wna16_gemm kernel is only "
|
||||
"available on CUDA platforms")
|
||||
torch.ops._moe_C.moe_wna16_gemm(input, output, b_qweight, b_scales,
|
||||
b_qzeros, topk_weights, sorted_token_ids,
|
||||
experts_ids, num_tokens_post_pad, top_k,
|
||||
|
||||
Reference in New Issue
Block a user