Add fp8 support to reshape_and_cache_flash (#6667)
This commit is contained in:
+2
-1
@@ -25,7 +25,8 @@ void reshape_and_cache_flash(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 std::string& kv_cache_dtype,
|
||||
const double k_scale, const double v_scale);
|
||||
|
||||
// Just for unittest
|
||||
void convert_fp8(torch::Tensor& dst_cache, torch::Tensor& src_cache,
|
||||
|
||||
Reference in New Issue
Block a user