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

ROCm Port (#1087)

Browse source 
* use hipblas based on cublas
* Update Makefile for the Cuda kernels
* Expand arch list and make it overrideable
* Fix multi GPU on multiple amd architectures with rocblas_initialize() (#5)
* add hipBLAS to README
* new build arg LLAMA_CUDA_MMQ_Y
* fix half2 decomposition
* Add intrinsics polyfills for AMD
* AMD assembly optimized __dp4a
* Allow overriding CC_TURING
* use "ROCm" instead of "CUDA"
* ignore all build dirs
* Add Dockerfiles
* fix llama-bench
* fix -nommq help for non CUDA/HIP

---------

Co-authored-by: YellowRoseCx <80486540+YellowRoseCx@users.noreply.github.com>
Co-authored-by: ardfork <134447697+ardfork@users.noreply.github.com>
Co-authored-by: funnbot <22226942+funnbot@users.noreply.github.com>
Co-authored-by: Engininja2 <139037756+Engininja2@users.noreply.github.com>
Co-authored-by: Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com>
Co-authored-by: jammm <2500920+jammm@users.noreply.github.com>
Co-authored-by: jdecourval <7315817+jdecourval@users.noreply.github.com>
This commit is contained in:
Henri Vasserman 2023-08-25 12:09:42 +03:00 • committed by GitHub
parent 3f460a2b72
commit 6bbc598a63
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
12 changed files with 335 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1836,7 +1836,7 @@ static void llm_load_tensors(
(void) main_gpu;
(void) mul_mat_q;
#if defined(GGML_USE_CUBLAS)
LLAMA_LOG_INFO("%s: using CUDA for GPU acceleration\n", __func__);
LLAMA_LOG_INFO("%s: using " GGML_CUDA_NAME " for GPU acceleration\n", __func__);
ggml_cuda_set_main_device(main_gpu);
ggml_cuda_set_mul_mat_q(mul_mat_q);
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_GPU