tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : GPU-accelerated token generation (#1412)

Browse Source 
* CUDA kernel for q4_0 dequant. + mat. vec. mult.

* Added q4_1 via template

* Added missing __syncthreads();

* --gpu_layers -> --gpu-layers

* Shorter dequantize_mul_mat_vec line

* q5_0 dequantize_mul_mat kernel

* More readable dequantize_mul_mat_vec logic

* dequantize_mul_mat_vec kernels for q5_1, q8_0, f16

* llama : offload "output" tensor to GPU too + coding style fixes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Johannes Gäßler
2023-05-13 15:38:36 +02:00
committed by GitHub
parent f954edda93
commit 905d87b70a
8 changed files with 336 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/common.cpp
View File

@ -277,6 +277,12 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.use_color = true;
} else if (arg == "--mlock") {
params.use_mlock = true;
} else if (arg == "--gpu-layers" || arg == "-ngl" || arg == "--n-gpu-layers") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.n_gpu_layers = std::stoi(argv[i]);
} else if (arg == "--no-mmap") {
params.use_mmap = false;
} else if (arg == "--mtest") {
@ -421,6 +427,8 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
if (llama_mmap_supported()) {
fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
}
fprintf(stderr, " -ngl N, --n-gpu-layers N\n");
fprintf(stderr, " number of layers to store in VRAM\n");
fprintf(stderr, " --mtest compute maximum memory usage\n");
fprintf(stderr, " --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
@ -463,14 +471,15 @@ std::vector<llama_token> llama_tokenize(struct llama_context * ctx, const std::s
struct llama_context * llama_init_from_gpt_params(const gpt_params & params) {
auto lparams = llama_context_default_params();
lparams.n_ctx = params.n_ctx;
lparams.n_parts = params.n_parts;
lparams.seed = params.seed;
lparams.f16_kv = params.memory_f16;
lparams.use_mmap = params.use_mmap;
lparams.use_mlock = params.use_mlock;
lparams.logits_all = params.perplexity;
lparams.embedding = params.embedding;
lparams.n_ctx = params.n_ctx;
lparams.n_parts = params.n_parts;
lparams.n_gpu_layers = params.n_gpu_layers;
lparams.seed = params.seed;
lparams.f16_kv = params.memory_f16;
lparams.use_mmap = params.use_mmap;
lparams.use_mlock = params.use_mlock;
lparams.logits_all = params.perplexity;
lparams.embedding = params.embedding;
llama_context * lctx = llama_init_from_file(params.model.c_str(), lparams);