ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

CUDA full GPU acceleration, KV cache in VRAM (#1827)

Browse source 
* Fixed CUDA RoPE

* ggml_cuda_mul_mat_vec_p021

* ggml_cuda_scale

* ggml_cuda_diag_mask_inf

* ggml_is_permuted

* ggml_cuda_cpy

* flatten rows for ggml_cuda_op

* Added a --low-vram option

* Fixed Windows performance

* Fixed LLAMA_CUDA_DMMV_Y > 1 for WizardLM
This commit is contained in:
Johannes Gäßler 2023-06-14 19:47:19 +02:00 • committed by GitHub
parent 9254920265
commit 254a7a7a5f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 853 additions and 149 deletions
Download patch file Download diff file Expand all files Collapse all files

9
examples/server/server.cpp
View file

@ -405,6 +405,7 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params &params)
fprintf(stderr, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
fprintf(stderr, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
fprintf(stderr, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n" );
fprintf(stderr, " -lv, --low-vram don't allocate VRAM scratch buffer\n" );
#endif
fprintf(stderr, " -m FNAME, --model FNAME\n");
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
@ -537,6 +538,14 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
}
#else
fprintf(stderr, "WARNING: llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n");
#endif // GGML_USE_CUBLAS
}
else if (arg == "--low-vram" || arg == "-lv")
{
#ifdef GGML_USE_CUBLAS
params.low_vram = true;
#else
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n");
#endif // GGML_USE_CUBLAS
}
else if (arg == "--main-gpu" || arg == "-mg")