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

update HIP_UMA #7399 (#7414)

Browse source 
* update HIP_UMA #7399

add use of hipMemAdviseSetCoarseGrain when LLAMA_HIP_UMA is enable.
- get x2 on prompte eval and x1.5 on token gen with rocm6.0 on ryzen 7940HX iGPU (780M/gfx1103)

* simplify code, more consistent style

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Djip007 2024-05-28 01:40:47 +02:00 • committed by GitHub
parent 0136966daf
commit 852aafb163
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 17 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml-cuda/common.cuh
View file

@ -79,13 +79,8 @@
#define cudaHostRegisterReadOnly hipHostRegisterReadOnly
#define cudaHostUnregister hipHostUnregister
#define cudaLaunchHostFunc hipLaunchHostFunc
#ifdef GGML_HIP_UMA
#define cudaMalloc hipMallocManaged
#define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size)
#else
#define cudaMalloc hipMalloc
#define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size, hipHostMallocDefault)
#endif
#define cudaMemcpy hipMemcpy
#define cudaMemcpyAsync hipMemcpyAsync
#define cudaMemcpyPeerAsync hipMemcpyPeerAsync