vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: Support Moore Threads GPU (#8383)

Browse source 
* Update doc for MUSA

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Add GGML_MUSA in Makefile

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Add GGML_MUSA in CMake

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* CUDA => MUSA

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* MUSA adds support for __vsubss4

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* Fix CI build failure

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
This commit is contained in:
R0CKSTAR 2024-07-28 07:41:25 +08:00 • committed by GitHub
parent 5e2727fe03
commit e54c35e4fb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 329 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

6
ggml/src/ggml-common.h
View file

@ -19,7 +19,11 @@ typedef half2 ggml_half2;
#define GGML_COMMON_DECL
#elif defined(GGML_COMMON_DECL_CUDA)
#if defined(GGML_COMMON_DECL_MUSA)
#include <musa_fp16.h>
#else
#include <cuda_fp16.h>
#endif
#include <cstdint>
typedef half ggml_half;
@ -415,7 +419,7 @@ static_assert(sizeof(block_iq4_xs) == sizeof(ggml_half) + sizeof(uint16_t) + QK_
#define GGML_TABLE_END() };
#define GGML_COMMON_IMPL
#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP)
#elif defined(GGML_COMMON_IMPL_CUDA) || defined(GGML_COMMON_IMPL_HIP) || defined(GGML_COMMON_IMPL_MUSA)
#include <cstdint>
#define GGML_TABLE_BEGIN(type, name, size) static const __device__ type name[size] = {