cuda : loading models directly into VRAM, norm calculation on GPU, broadcasting for ggml_mul (#1483)
* Broadcasting for ggml_mul * CUDA kernel for ggml_mul, norms in VRAM * GPU weights not in RAM, direct loading with cuFile * fixup! GPU weights not in RAM, direct loading with cuFile * fixup! GPU weights not in RAM, direct loading with cuFile * define default model path once, sync path with readme (#1366) * ~7% faster Q5_1 AVX2 code (#1477) * convert.py: Support models which are stored in a single pytorch_model.bin (#1469) * Support models in a single pytorch_model.bin * Remove spurious line with typo * benchmark-matmul: Print the average of the test results (#1490) * Remove unused n_parts parameter (#1509) * Fixes #1511 lambda issue for w64devkit (mingw) (#1513) * Fix for w64devkit and mingw * make kv_f16 the default for api users (#1517) * minor : fix compile warnings * readme : adds WizardLM to the list of supported models (#1485) * main : make reverse prompt option act as a stop token in non-interactive mode (#1032) * Make reverse prompt option act as a stop token in non-interactive scenarios * Making requested review changes * Update gpt_params_parse and fix a merge error * Revert "Update gpt_params_parse and fix a merge error" This reverts commit2bb2ff1748. * Update gpt_params_parse and fix a merge error take 2 * examples : add persistent chat (#1495) * examples : add persistent chat * examples : fix whitespace --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * tests : add missing header * ggml : use F16 instead of F32 in Q4_0, Q4_1, Q8_0 (#1508) * ggml : use F16 instead of F32 in Q4_0, Q4_1 and Q8_0 * llama : bump LLAMA_FILE_VERSION to 3 * cuda : update Q4 and Q8 dequantize kernels * ggml : fix AVX dot products * readme : update performance table + hot topics * ggml : fix scalar implementation of Q4_1 dot * llama : fix compile warnings in llama_set_state_data() * llama : fix name shadowing and C4146 (#1526) * Fix name shadowing and C4146 * Fix if macros not using defined when required * Update llama-util.h Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Update llama-util.h Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> * Code style Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Fix for mingw (#1462) * llama : add llama_init_backend() API (close #1527) * feature : add blis and other BLAS implementation support (#1502) * feature: add blis support * feature: allow all BLA_VENDOR to be assigned in cmake arguments. align with whisper.cpp pr 927 * fix: version detection for BLA_SIZEOF_INTEGER, recover min version of cmake * Fix typo in INTEGER Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Revert "feature : add blis and other BLAS implementation support (#1502)" This reverts commit07e9ace0f9. * GPU weights not in RAM, direct loading with cuFile * llama : code style fixes + progress print fix * ggml : ggml_mul better broadcast support * cmake : workarounds for cufile when CMake version < 3.25 * gg rebase fixup * Loop in llama.cpp, fixed progress callback * Attempt clang-tidy fix * llama : fix vram size computation * Add forgotten fclose() --------- Co-authored-by: András Salamon <ott2@users.noreply.github.com> Co-authored-by: Ilya Kurdyukov <59548320+ilyakurdyukov@users.noreply.github.com> Co-authored-by: Tom Jobbins <784313+TheBloke@users.noreply.github.com> Co-authored-by: rankaiyx <rankaiyx@rankaiyx.com> Co-authored-by: Stephan Walter <stephan@walter.name> Co-authored-by: DannyDaemonic <DannyDaemonic@gmail.com> Co-authored-by: Erik Scholz <Green-Sky@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: David Kennedy <dakennedyd@gmail.com> Co-authored-by: Jason McCartney <jmac@theroot.org> Co-authored-by: Evan Jones <evan.q.jones@gmail.com> Co-authored-by: Maxime <672982+maximegmd@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Zenix <zenixls2@gmail.com>
This commit is contained in:
Johannes Gäßler
GitHub
parent
ea600071cb
commit
affc76edfd
5 changed files with 304 additions and 116 deletions
199
llama.cpp
199
llama.cpp
|
|
@ -1,6 +1,7 @@
|
|||
// Defines fileno on msys:
|
||||
#ifndef _GNU_SOURCE
|
||||
#define _GNU_SOURCE
|
||||
#include <cstddef>
|
||||
#include <cstdint>
|
||||
#include <cstdio>
|
||||
#endif
|
||||
|
|
@ -645,7 +646,7 @@ struct llama_model_loader {
|
|||
}
|
||||
}
|
||||
|
||||
struct ggml_tensor * get_tensor(const std::string & name, const std::vector<uint32_t> & ne) {
|
||||
struct ggml_tensor * get_tensor(const std::string & name, const std::vector<uint32_t> & ne, ggml_backend backend) {
|
||||
auto it = tensors_map.name_to_idx.find(name);
|
||||
if (it == tensors_map.name_to_idx.end()) {
|
||||
throw format("llama.cpp: tensor '%s' is missing from model", name.c_str());
|
||||
|
|
@ -656,10 +657,10 @@ struct llama_model_loader {
|
|||
name.c_str(), llama_format_tensor_shape(ne).c_str(), llama_format_tensor_shape(lt.ne).c_str());
|
||||
}
|
||||
|
||||
return get_tensor_for(lt);
|
||||
return get_tensor_for(lt, backend);
|
||||
}
|
||||
|
||||
struct ggml_tensor * get_tensor_for(llama_load_tensor & lt) {
|
||||
struct ggml_tensor * get_tensor_for(llama_load_tensor & lt, ggml_backend backend) {
|
||||
struct ggml_tensor * tensor;
|
||||
if (lt.ne.size() == 2) {
|
||||
tensor = ggml_new_tensor_2d(ggml_ctx, lt.type, lt.ne.at(0), lt.ne.at(1));
|
||||
|
|
@ -669,6 +670,7 @@ struct llama_model_loader {
|
|||
}
|
||||
ggml_set_name(tensor, lt.name.c_str());
|
||||
LLAMA_ASSERT(lt.ggml_tensor == NULL); // if this fails, we called get_tensor twice on the same tensor
|
||||
tensor->backend = backend;
|
||||
lt.ggml_tensor = tensor;
|
||||
num_ggml_tensors_created++;
|
||||
return tensor;
|
||||
|
|
@ -682,12 +684,16 @@ struct llama_model_loader {
|
|||
|
||||
void load_all_data(llama_progress_callback progress_callback, void * progress_callback_user_data, llama_mlock * lmlock) {
|
||||
size_t data_size = 0;
|
||||
size_t prefetch_size = 0;
|
||||
for (const llama_load_tensor & lt : tensors_map.tensors) {
|
||||
data_size += lt.size;
|
||||
if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) {
|
||||
prefetch_size += lt.size;
|
||||
}
|
||||
}
|
||||
|
||||
if (use_mmap) {
|
||||
mapping.reset(new llama_mmap(&file_loaders.at(0)->file));
|
||||
mapping.reset(new llama_mmap(&file_loaders.at(0)->file, prefetch_size));
|
||||
if (!lmlock) {
|
||||
// Don't call the callback since the actual loading will be lazy
|
||||
// and we can't measure it.
|
||||
|
|
@ -700,6 +706,9 @@ struct llama_model_loader {
|
|||
|
||||
size_t done_size = 0;
|
||||
for (llama_load_tensor & lt : tensors_map.tensors) {
|
||||
if (lt.ggml_tensor->backend != GGML_BACKEND_CPU) {
|
||||
continue;
|
||||
}
|
||||
if (progress_callback) {
|
||||
progress_callback((float) done_size / data_size, progress_callback_user_data);
|
||||
}
|
||||
|
|
@ -712,9 +721,6 @@ struct llama_model_loader {
|
|||
lmlock->grow_to(done_size);
|
||||
}
|
||||
}
|
||||
if (progress_callback) {
|
||||
progress_callback(1.0f, progress_callback_user_data);
|
||||
}
|
||||
}
|
||||
|
||||
void load_data_for(llama_load_tensor & lt) {
|
||||
|
|
@ -969,27 +975,7 @@ static void llama_model_load_internal(
|
|||
size_t ctx_size;
|
||||
size_t mmapped_size;
|
||||
ml->calc_sizes(&ctx_size, &mmapped_size);
|
||||
fprintf(stderr, "%s: ggml ctx size = %6.2f MB\n", __func__, ctx_size/1024.0/1024.0);
|
||||
|
||||
// print memory requirements
|
||||
{
|
||||
const size_t scale = memory_type == GGML_TYPE_F32 ? 2 : 1;
|
||||
|
||||
// this is the total memory required to run the inference
|
||||
const size_t mem_required =
|
||||
ctx_size +
|
||||
mmapped_size +
|
||||
MEM_REQ_SCRATCH0().at(model.type) +
|
||||
MEM_REQ_SCRATCH1().at(model.type) +
|
||||
MEM_REQ_EVAL().at(model.type);
|
||||
|
||||
// this is the memory required by one llama_state
|
||||
const size_t mem_required_state =
|
||||
scale*MEM_REQ_KV_SELF().at(model.type);
|
||||
|
||||
fprintf(stderr, "%s: mem required = %7.2f MB (+ %7.2f MB per state)\n", __func__,
|
||||
mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
|
||||
}
|
||||
fprintf(stderr, "%s: ggml ctx size = %7.2f MB\n", __func__, ctx_size/1024.0/1024.0);
|
||||
|
||||
// create the ggml context
|
||||
{
|
||||
|
|
@ -1011,7 +997,14 @@ static void llama_model_load_internal(
|
|||
}
|
||||
}
|
||||
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CUDA
|
||||
#else
|
||||
#define LLAMA_BACKEND_OFFLOAD GGML_BACKEND_CPU
|
||||
#endif
|
||||
|
||||
// prepare memory for the weights
|
||||
size_t vram_total = 0;
|
||||
{
|
||||
const uint32_t n_embd = hparams.n_embd;
|
||||
const uint32_t n_layer = hparams.n_layer;
|
||||
|
|
@ -1019,33 +1012,87 @@ static void llama_model_load_internal(
|
|||
|
||||
ml->ggml_ctx = ctx;
|
||||
|
||||
model.tok_embeddings = ml->get_tensor("tok_embeddings.weight", {n_embd, n_vocab});
|
||||
model.norm = ml->get_tensor("norm.weight", {n_embd});
|
||||
model.output = ml->get_tensor("output.weight", {n_embd, n_vocab});
|
||||
model.tok_embeddings = ml->get_tensor("tok_embeddings.weight", {n_embd, n_vocab}, GGML_BACKEND_CPU);
|
||||
model.norm = ml->get_tensor("norm.weight", {n_embd}, GGML_BACKEND_CPU);
|
||||
|
||||
// "output" tensor
|
||||
{
|
||||
ggml_backend backend_output;
|
||||
if (n_gpu_layers > int(n_layer)) { // NOLINT
|
||||
backend_output = LLAMA_BACKEND_OFFLOAD;
|
||||
} else {
|
||||
backend_output = GGML_BACKEND_CPU;
|
||||
}
|
||||
|
||||
model.output = ml->get_tensor("output.weight", {n_embd, n_vocab}, backend_output);
|
||||
}
|
||||
|
||||
const int i_gpu_start = n_layer - n_gpu_layers;
|
||||
|
||||
model.layers.resize(n_layer);
|
||||
for (uint32_t i = 0; i < n_layer; ++i) {
|
||||
const ggml_backend backend = int(i) < i_gpu_start ? GGML_BACKEND_CPU : LLAMA_BACKEND_OFFLOAD;
|
||||
|
||||
auto & layer = model.layers[i];
|
||||
|
||||
std::string layers_i = "layers." + std::to_string(i);
|
||||
|
||||
layer.attention_norm = ml->get_tensor(layers_i + ".attention_norm.weight", {n_embd});
|
||||
layer.attention_norm = ml->get_tensor(layers_i + ".attention_norm.weight", {n_embd}, backend);
|
||||
|
||||
layer.wq = ml->get_tensor(layers_i + ".attention.wq.weight", {n_embd, n_embd});
|
||||
layer.wk = ml->get_tensor(layers_i + ".attention.wk.weight", {n_embd, n_embd});
|
||||
layer.wv = ml->get_tensor(layers_i + ".attention.wv.weight", {n_embd, n_embd});
|
||||
layer.wo = ml->get_tensor(layers_i + ".attention.wo.weight", {n_embd, n_embd});
|
||||
layer.wq = ml->get_tensor(layers_i + ".attention.wq.weight", {n_embd, n_embd}, backend);
|
||||
layer.wk = ml->get_tensor(layers_i + ".attention.wk.weight", {n_embd, n_embd}, backend);
|
||||
layer.wv = ml->get_tensor(layers_i + ".attention.wv.weight", {n_embd, n_embd}, backend);
|
||||
layer.wo = ml->get_tensor(layers_i + ".attention.wo.weight", {n_embd, n_embd}, backend);
|
||||
|
||||
layer.ffn_norm = ml->get_tensor(layers_i + ".ffn_norm.weight", {n_embd});
|
||||
layer.ffn_norm = ml->get_tensor(layers_i + ".ffn_norm.weight", {n_embd}, backend);
|
||||
|
||||
layer.w1 = ml->get_tensor(layers_i + ".feed_forward.w1.weight", {n_embd, n_ff});
|
||||
layer.w2 = ml->get_tensor(layers_i + ".feed_forward.w2.weight", { n_ff, n_embd});
|
||||
layer.w3 = ml->get_tensor(layers_i + ".feed_forward.w3.weight", {n_embd, n_ff});
|
||||
layer.w1 = ml->get_tensor(layers_i + ".feed_forward.w1.weight", {n_embd, n_ff}, backend);
|
||||
layer.w2 = ml->get_tensor(layers_i + ".feed_forward.w2.weight", { n_ff, n_embd}, backend);
|
||||
layer.w3 = ml->get_tensor(layers_i + ".feed_forward.w3.weight", {n_embd, n_ff}, backend);
|
||||
|
||||
if (backend == GGML_BACKEND_CUDA) {
|
||||
vram_total +=
|
||||
ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) +
|
||||
ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) +
|
||||
ggml_nbytes(layer.w1) + ggml_nbytes(layer.w2) + ggml_nbytes(layer.w3);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ml->done_getting_tensors();
|
||||
|
||||
// print memory requirements
|
||||
{
|
||||
const size_t scale = memory_type == GGML_TYPE_F32 ? 2 : 1;
|
||||
|
||||
// this is the total memory required to run the inference
|
||||
const size_t mem_required =
|
||||
ctx_size +
|
||||
mmapped_size - vram_total + // weights in VRAM not in memory
|
||||
MEM_REQ_SCRATCH0().at(model.type) +
|
||||
MEM_REQ_SCRATCH1().at(model.type) +
|
||||
MEM_REQ_EVAL().at(model.type);
|
||||
|
||||
// this is the memory required by one llama_state
|
||||
const size_t mem_required_state =
|
||||
scale*MEM_REQ_KV_SELF().at(model.type);
|
||||
|
||||
fprintf(stderr, "%s: mem required = %7.2f MB (+ %7.2f MB per state)\n", __func__,
|
||||
mem_required / 1024.0 / 1024.0, mem_required_state / 1024.0 / 1024.0);
|
||||
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
|
||||
|
||||
fprintf(stderr, "%s: [cublas] offloading %d layers to GPU\n", __func__, n_gpu);
|
||||
if (n_gpu_layers > (int) hparams.n_layer) {
|
||||
fprintf(stderr, "%s: [cublas] offloading output layer to GPU\n", __func__);
|
||||
}
|
||||
fprintf(stderr, "%s: [cublas] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
|
||||
#else
|
||||
(void) n_gpu_layers;
|
||||
#endif
|
||||
}
|
||||
|
||||
// populate `tensors_by_name`
|
||||
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
|
||||
model.tensors_by_name.emplace_back(lt.name, lt.ggml_tensor);
|
||||
|
|
@ -1053,36 +1100,34 @@ static void llama_model_load_internal(
|
|||
|
||||
ml->load_all_data(progress_callback, progress_callback_user_data, use_mlock ? &lctx.model.mlock_mmap : NULL);
|
||||
|
||||
model.mapping = std::move(ml->mapping);
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
{
|
||||
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
|
||||
|
||||
fprintf(stderr, "%s: [cublas] offloading %d layers to GPU\n", __func__, n_gpu);
|
||||
|
||||
size_t vram_total = 0;
|
||||
|
||||
for (int i = 0; i < n_gpu; ++i) {
|
||||
const auto & layer = model.layers[i];
|
||||
|
||||
ggml_cuda_transform_tensor(layer.wq); vram_total += ggml_nbytes(layer.wq);
|
||||
ggml_cuda_transform_tensor(layer.wk); vram_total += ggml_nbytes(layer.wk);
|
||||
ggml_cuda_transform_tensor(layer.wv); vram_total += ggml_nbytes(layer.wv);
|
||||
ggml_cuda_transform_tensor(layer.wo); vram_total += ggml_nbytes(layer.wo);
|
||||
ggml_cuda_transform_tensor(layer.w1); vram_total += ggml_nbytes(layer.w1);
|
||||
ggml_cuda_transform_tensor(layer.w2); vram_total += ggml_nbytes(layer.w2);
|
||||
ggml_cuda_transform_tensor(layer.w3); vram_total += ggml_nbytes(layer.w3);
|
||||
size_t done_size = 0;
|
||||
size_t data_size = 0;
|
||||
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
|
||||
data_size += lt.size;
|
||||
if (lt.ggml_tensor->backend == GGML_BACKEND_CPU) {
|
||||
done_size += lt.size;
|
||||
}
|
||||
}
|
||||
if (n_gpu_layers > (int) hparams.n_layer) {
|
||||
fprintf(stderr, "%s: [cublas] offloading output layer to GPU\n", __func__);
|
||||
ggml_cuda_transform_tensor(model.output); vram_total += ggml_nbytes(model.output);
|
||||
for (llama_load_tensor & lt : ml->tensors_map.tensors) {
|
||||
if (lt.ggml_tensor->backend != GGML_BACKEND_CUDA) {
|
||||
continue;
|
||||
}
|
||||
if (progress_callback) {
|
||||
progress_callback((float) done_size / data_size, progress_callback_user_data);
|
||||
}
|
||||
ggml_cuda_load_data(fname.c_str(), lt.ggml_tensor, lt.shards.at(0).file_off);
|
||||
done_size += lt.size;
|
||||
}
|
||||
|
||||
fprintf(stderr, "%s: [cublas] total VRAM used: %zu MB\n", __func__, vram_total / 1024 / 1024);
|
||||
}
|
||||
#else
|
||||
(void) n_gpu_layers;
|
||||
#endif
|
||||
#endif // GGML_USE_CUBLAS
|
||||
|
||||
if (progress_callback) {
|
||||
progress_callback(1.0f, progress_callback_user_data);
|
||||
}
|
||||
|
||||
model.mapping = std::move(ml->mapping);
|
||||
|
||||
// loading time will be recalculate after the first eval, so
|
||||
// we take page faults deferred by mmap() into consideration
|
||||
|
|
@ -1181,10 +1226,8 @@ static bool llama_eval_internal(
|
|||
{
|
||||
cur = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
// cur = attention_norm*cur
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model.layers[il].attention_norm, cur),
|
||||
cur);
|
||||
// cur = cur*attention_norm(broadcasted)
|
||||
cur = ggml_mul(ctx0, cur, model.layers[il].attention_norm);
|
||||
}
|
||||
|
||||
// self-attention
|
||||
|
|
@ -1291,10 +1334,8 @@ static bool llama_eval_internal(
|
|||
{
|
||||
cur = ggml_rms_norm(ctx0, inpFF);
|
||||
|
||||
// cur = ffn_norm*cur
|
||||
cur = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model.layers[il].ffn_norm, cur),
|
||||
cur);
|
||||
// cur = cur*ffn_norm(broadcasted)
|
||||
cur = ggml_mul(ctx0, cur, model.layers[il].ffn_norm);
|
||||
}
|
||||
|
||||
struct ggml_tensor * tmp = ggml_mul_mat(ctx0,
|
||||
|
|
@ -1331,10 +1372,8 @@ static bool llama_eval_internal(
|
|||
|
||||
inpL = ggml_rms_norm(ctx0, inpL);
|
||||
|
||||
// inpL = norm*inpL
|
||||
inpL = ggml_mul(ctx0,
|
||||
ggml_repeat(ctx0, model.norm, inpL),
|
||||
inpL);
|
||||
// inpL = inpL*norm(broadcasted)
|
||||
inpL = ggml_mul(ctx0, inpL, model.norm);
|
||||
|
||||
embeddings = inpL;
|
||||
}
|
||||
|
|
@ -2158,7 +2197,7 @@ struct llama_context * llama_init_from_file(
|
|||
unsigned * cur_percentage_p = (unsigned *) ctx;
|
||||
unsigned percentage = (unsigned) (100 * progress);
|
||||
while (percentage > *cur_percentage_p) {
|
||||
++*cur_percentage_p;
|
||||
*cur_percentage_p = percentage;
|
||||
fprintf(stderr, ".");
|
||||
fflush(stderr);
|
||||
if (percentage >= 100) {
|
||||
|
|
@ -2315,7 +2354,7 @@ int llama_apply_lora_from_file_internal(struct llama_context * ctx, const char *
|
|||
|
||||
// maybe this should in llama_model_loader
|
||||
if (model_loader->use_mmap) {
|
||||
model_loader->mapping.reset(new llama_mmap(&model_loader->file_loaders.at(0)->file, /* prefetch */ false));
|
||||
model_loader->mapping.reset(new llama_mmap(&model_loader->file_loaders.at(0)->file, /* prefetch */ 0));
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -2408,7 +2447,7 @@ int llama_apply_lora_from_file_internal(struct llama_context * ctx, const char *
|
|||
}
|
||||
size_t idx = model_loader->tensors_map.name_to_idx[base_name];
|
||||
llama_load_tensor & lt = model_loader->tensors_map.tensors[idx];
|
||||
base_t = model_loader->get_tensor(base_name, { (uint32_t)dest_t->ne[0], (uint32_t)dest_t->ne[1] });
|
||||
base_t = model_loader->get_tensor(base_name, { (uint32_t)dest_t->ne[0], (uint32_t)dest_t->ne[1] }, GGML_BACKEND_CPU);
|
||||
lt.data = (uint8_t *) lt.ggml_tensor->data;
|
||||
model_loader->load_data_for(lt);
|
||||
lt.ggml_tensor->data = lt.data;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue