biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Attention] MLA with chunked prefill (#12639)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patrick Horn <patrick.horn@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson
2025-02-21 18:30:12 -05:00
committed by GitHub
parent 900edbfa48
commit 288cc6c234
18 changed files with 1910 additions and 1275 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
csrc/cuda_utils.h
View File

@@ -2,10 +2,14 @@
#include <stdio.h>
#if defined(__CUDACC__) || defined(_NVHPC_CUDA)
#define HOST_DEVICE_INLINE __forceinline__ __host__ __device__
#define DEVICE_INLINE __forceinline__ __device__
#define HOST_INLINE __forceinline__ __host__
#if defined(__HIPCC__)
#define HOST_DEVICE_INLINE __host__ __device__
#define DEVICE_INLINE __device__
#define HOST_INLINE __host__
#elif defined(__CUDACC__) || defined(_NVHPC_CUDA)
#define HOST_DEVICE_INLINE __host__ __device__ __forceinline__
#define DEVICE_INLINE __device__ __forceinline__
#define HOST_INLINE __host__ __forceinline__
#else
#define HOST_DEVICE_INLINE inline
#define DEVICE_INLINE inline
@@ -25,3 +29,13 @@
int64_t get_device_attribute(int64_t attribute, int64_t device_id);
int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);
namespace cuda_utils {
template <typename T>
HOST_DEVICE_INLINE constexpr std::enable_if_t<std::is_integral_v<T>, T>
ceil_div(T a, T b) {
return (a + b - 1) / b;
}
}; // namespace cuda_utils