Skip to content

Commit cb206e6

Browse files
committed
fix comments
Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>
1 parent fba2010 commit cb206e6

1 file changed

Lines changed: 1 addition & 2 deletions

File tree

cpp/tensorrt_llm/thop/attentionOp.h

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -78,8 +78,7 @@ void attention(torch::Tensor q, std::optional<torch::Tensor> k, std::optional<to
7878
std::optional<torch::Tensor> fmha_scheduler_counter, std::optional<torch::Tensor> mla_bmm1_scale,
7979
std::optional<torch::Tensor> mla_bmm2_scale, std::optional<torch::Tensor> quant_q_buffer,
8080
std::optional<torch::Tensor> flash_mla_tile_scheduler_metadata = std::nullopt,
81-
std::optional<torch::Tensor> flash_mla_num_splits = std::nullopt,
82-
int64_t num_contexts = 0,
81+
std::optional<torch::Tensor> flash_mla_num_splits = std::nullopt, int64_t num_contexts = 0,
8382
int64_t num_ctx_tokens = 0);
8483

8584
struct KvCachePoolPointers

0 commit comments

Comments
 (0)