[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081)
This commit is contained in:
+2
-2
@@ -18,8 +18,8 @@ void copy_blocks(std::vector<torch::Tensor> const& key_caches,
|
||||
void reshape_and_cache(torch::Tensor& key, torch::Tensor& value,
|
||||
torch::Tensor& key_cache, torch::Tensor& value_cache,
|
||||
torch::Tensor& slot_mapping,
|
||||
const std::string& kv_cache_dtype,
|
||||
const double kv_scale);
|
||||
const std::string& kv_cache_dtype, const double k_scale,
|
||||
const double v_scale);
|
||||
|
||||
void reshape_and_cache_flash(torch::Tensor& key, torch::Tensor& value,
|
||||
torch::Tensor& key_cache,
|
||||
|
||||
Reference in New Issue
Block a user