[Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (#4535)
This commit is contained in:
+3
-1
@@ -34,5 +34,7 @@ void reshape_and_cache_flash(
|
||||
|
||||
// Just for unittest
|
||||
void convert_fp8(
|
||||
torch::Tensor& dst_cache,
|
||||
torch::Tensor& src_cache,
|
||||
torch::Tensor& dst_cache);
|
||||
const float scale,
|
||||
const std::string& kv_cache_dtype);
|
||||
|
||||
Reference in New Issue
Block a user