[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)
This commit is contained in:
+4
-4
@@ -8,8 +8,8 @@ void paged_attention_v1(
|
||||
torch::Tensor& value_cache, int64_t num_kv_heads, double scale,
|
||||
torch::Tensor& block_tables, torch::Tensor& seq_lens, int64_t block_size,
|
||||
int64_t max_seq_len, const c10::optional<torch::Tensor>& alibi_slopes,
|
||||
const std::string& kv_cache_dtype, double kv_scale, const int64_t tp_rank,
|
||||
const int64_t blocksparse_local_blocks,
|
||||
const std::string& kv_cache_dtype, double k_scale, double v_scale,
|
||||
const int64_t tp_rank, const int64_t blocksparse_local_blocks,
|
||||
const int64_t blocksparse_vert_stride, const int64_t blocksparse_block_size,
|
||||
const int64_t blocksparse_head_sliding_step);
|
||||
|
||||
@@ -19,8 +19,8 @@ void paged_attention_v2(
|
||||
torch::Tensor& value_cache, int64_t num_kv_heads, double scale,
|
||||
torch::Tensor& block_tables, torch::Tensor& seq_lens, int64_t block_size,
|
||||
int64_t max_seq_len, const c10::optional<torch::Tensor>& alibi_slopes,
|
||||
const std::string& kv_cache_dtype, double kv_scale, const int64_t tp_rank,
|
||||
const int64_t blocksparse_local_blocks,
|
||||
const std::string& kv_cache_dtype, double k_scale, double v_scale,
|
||||
const int64_t tp_rank, const int64_t blocksparse_local_blocks,
|
||||
const int64_t blocksparse_vert_stride, const int64_t blocksparse_block_size,
|
||||
const int64_t blocksparse_head_sliding_step);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user