[Deepseek v3.2] Optimize top_k_per_row (#26763)
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
This commit is contained in:
+1
-2
@@ -99,8 +99,7 @@ void apply_repetition_penalties_(torch::Tensor& logits,
|
||||
|
||||
void top_k_per_row(const torch::Tensor& logits, const torch::Tensor& rowStarts,
|
||||
const torch::Tensor& rowEnds, torch::Tensor& indices,
|
||||
torch::Tensor& values, int64_t numRows, int64_t stride0,
|
||||
int64_t stride1);
|
||||
int64_t numRows, int64_t stride0, int64_t stride1);
|
||||
|
||||
void rms_norm_static_fp8_quant(torch::Tensor& out, torch::Tensor& input,
|
||||
torch::Tensor& weight, torch::Tensor& scale,
|
||||
|
||||
Reference in New Issue
Block a user