[Kernel] Add router GEMM kernels for (5120, 256) and BF16 output to ll_bf16_gemm (#62042)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai> Co-authored-by: Lain <fusiyuan2000@gmail.com> Co-authored-by: Codex <noreply@openai.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: vllm-agent <claw@inferact.ai>
This commit is contained in:
co-authored by
Lain
Codex
Claude Opus 5.5
vllm-agent
parent
153a17166e
commit
596e530675
@@ -2424,6 +2424,11 @@ def grouped_topk(
|
||||
raise NotImplementedError(
|
||||
"The fused grouped_topk kernel is only available on CUDA and XPU platforms"
|
||||
)
|
||||
if scores.shape[0] == 0:
|
||||
return (
|
||||
scores.new_empty((0, topk), dtype=torch.float32),
|
||||
scores.new_empty((0, topk), dtype=torch.int32),
|
||||
)
|
||||
return torch.ops._moe_C.grouped_topk(
|
||||
scores,
|
||||
num_expert_group,
|
||||
|
||||
Reference in New Issue
Block a user