Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

GPU-accelerated token generation (new quantization format) #1412

Merged
merged 9 commits into from
May 13, 2023
+336 −42
Merged

GPU-accelerated token generation (new quantization format) #1412

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
637be12
CUDA kernel for q4_0 dequant. + mat. vec. mult.
JohannesGaessler May 8, 2023
12fc292
Added q4_1 via template
JohannesGaessler May 12, 2023
7dc2f57
Added missing __syncthreads();
JohannesGaessler May 12, 2023
f0af475
--gpu_layers -> --gpu-layers
JohannesGaessler May 12, 2023
0986c2f
Shorter dequantize_mul_mat_vec line
JohannesGaessler May 12, 2023
9da44fd
q5_0 dequantize_mul_mat kernel
JohannesGaessler May 12, 2023
5a0ecf7
More readable dequantize_mul_mat_vec logic
JohannesGaessler May 13, 2023
bb0993e
dequantize_mul_mat_vec kernels for q5_1, q8_0, f16
JohannesGaessler May 13, 2023
ad8a9e6
llama : offload "output" tensor to GPU too + coding style fixes
ggerganov May 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 17 additions & 8 deletions examples/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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") {
Expand Down Expand Up @@ -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");
Expand Down Expand Up @@ -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);

Expand Down
11 changes: 6 additions & 5 deletions examples/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,13 +21,14 @@
int32_t get_num_physical_cores();

struct gpt_params {
int32_t seed = -1; // RNG seed
int32_t seed = -1; // RNG seed
int32_t n_threads = get_num_physical_cores();
int32_t n_predict = -1; // new tokens to predict
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
int32_t n_gpu_layers = 0; // number of layers to store in VRAM

// sampling parameters
std::unordered_map<llama_token, float> logit_bias; // logit bias for specific tokens
Expand Down
Loading