Sync from v0.13
This commit is contained in:
11
csrc/quantization/cutlass_w4a8/w4a8_utils.cuh
Normal file
11
csrc/quantization/cutlass_w4a8/w4a8_utils.cuh
Normal file
@@ -0,0 +1,11 @@
|
||||
#pragma once
|
||||
|
||||
#include <cstddef>
|
||||
#include "cutlass/numeric_types.h"
|
||||
|
||||
namespace vllm::cutlass_w4a8_utils {
|
||||
|
||||
bool unified_encode_int4b(cutlass::int4b_t const* in, cutlass::int4b_t* out,
|
||||
size_t num_int4_elems);
|
||||
|
||||
} // namespace vllm::cutlass_w4a8_utils
|
||||
Reference in New Issue
Block a user