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

Merge branch 'master' into compilade/convert-hf-refactor

Browse source
This commit is contained in:
Francis Couture-Harpin 2024-04-30 14:08:05 -04:00
commit 0d720acb91
30 changed files with 3316 additions and 739 deletions
Download patch file Download diff file Expand all files Collapse all files

28
examples/batched-bench/batched-bench.cpp
View file

@ -32,7 +32,7 @@ int main(int argc, char ** argv) {
gpt_params params;
if (argc == 1 || argv[1][0] == '-') {
printf("usage: %s MODEL_PATH [N_KV_MAX] [N_BATCH] [N_UBATCH] [IS_PP_SHARED] [NGL] <PP> <TG> <PL>\n" , argv[0]);
printf("usage: %s MODEL_PATH [N_KV_MAX] [N_BATCH] [N_UBATCH] [FATTN] [IS_PP_SHARED] [NGL] <PP> <TG> <PL>\n" , argv[0]);
printf(" <PP>, <TG> and PL are comma-separated lists of numbers without spaces\n\n");
printf(" example: %s ggml-model-f16.gguf 2048 2048 512 0 999 128,256,512 128,256 1,2,4,8,16,32\n\n", argv[0]);
return 1 ;
@ -41,6 +41,7 @@ int main(int argc, char ** argv) {
int n_kv_max = 2048;
int n_batch = 2048;
int n_ubatch = 512;
bool flash_attn = false;
int is_pp_shared = 0;
int n_gpu_layers = 0;
@ -66,23 +67,27 @@ int main(int argc, char ** argv) {
}
if (argc >= 6) {
is_pp_shared = std::atoi(argv[5]);
flash_attn = std::atoi(argv[5]);
}
if (argc >= 7) {
n_gpu_layers = std::atoi(argv[6]);
is_pp_shared = std::atoi(argv[6]);
}
if (argc >= 8) {
n_pp = parse_list(argv[7]);
n_gpu_layers = std::atoi(argv[7]);
}
if (argc >= 9) {
n_tg = parse_list(argv[8]);
n_pp = parse_list(argv[8]);
}
if (argc >= 10) {
n_pl = parse_list(argv[9]);
n_tg = parse_list(argv[9]);
}
if (argc >= 11) {
n_pl = parse_list(argv[10]);
}
// init LLM
@ -108,10 +113,11 @@ int main(int argc, char ** argv) {
llama_context_params ctx_params = llama_context_default_params();
ctx_params.seed = 1234;
ctx_params.n_ctx = n_kv_max;
ctx_params.n_batch = n_batch;
ctx_params.n_ubatch = n_ubatch;
ctx_params.seed = 1234;
ctx_params.n_ctx = n_kv_max;
ctx_params.n_batch = n_batch;
ctx_params.n_ubatch = n_ubatch;
ctx_params.flash_attn = flash_attn;
ctx_params.n_threads = params.n_threads;
ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
@ -169,7 +175,7 @@ int main(int argc, char ** argv) {
}
LOG_TEE("\n");
LOG_TEE("%s: n_kv_max = %d, n_batch = %d, n_ubatch = %d, is_pp_shared = %d, n_gpu_layers = %d, n_threads = %u, n_threads_batch = %u\n", __func__, n_kv_max, n_batch, n_ubatch, is_pp_shared, n_gpu_layers, ctx_params.n_threads, ctx_params.n_threads_batch);
LOG_TEE("%s: n_kv_max = %d, n_batch = %d, n_ubatch = %d, flash_attn = %d, is_pp_shared = %d, n_gpu_layers = %d, n_threads = %u, n_threads_batch = %u\n", __func__, n_kv_max, n_batch, n_ubatch, flash_attn, is_pp_shared, n_gpu_layers, ctx_params.n_threads, ctx_params.n_threads_batch);
LOG_TEE("\n");
LOG_TEE("|%6s | %6s | %4s | %6s | %8s | %8s | %8s | %8s | %8s | %8s |\n", "PP", "TG", "B", "N_KV", "T_PP s", "S_PP t/s", "T_TG s", "S_TG t/s", "T s", "S t/s");

30
examples/llama-bench/llama-bench.cpp
View file

@ -174,6 +174,7 @@ struct cmd_params {
std::vector<llama_split_mode> split_mode;
std::vector<int> main_gpu;
std::vector<bool> no_kv_offload;
std::vector<bool> flash_attn;
std::vector<std::vector<float>> tensor_split;
std::vector<bool> use_mmap;
std::vector<bool> embeddings;
@ -195,6 +196,7 @@ static const cmd_params cmd_params_defaults = {
/* split_mode */ {LLAMA_SPLIT_MODE_LAYER},
/* main_gpu */ {0},
/* no_kv_offload */ {false},
/* flash_attn */ {false},
/* tensor_split */ {std::vector<float>(llama_max_devices(), 0.0f)},
/* use_mmap */ {true},
/* embeddings */ {false},
@ -220,6 +222,7 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" -sm, --split-mode <none|layer|row> (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
printf(" -mg, --main-gpu <i> (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
printf(" -nkvo, --no-kv-offload <0|1> (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
printf(" -fa, --flash-attn <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str());
printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str());
printf(" -embd, --embeddings <0|1> (default: %s)\n", join(cmd_params_defaults.embeddings, ",").c_str());
printf(" -ts, --tensor-split <ts0/ts1/..> (default: 0)\n");
@ -393,6 +396,13 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
}
auto p = split<bool>(argv[i], split_delim);
params.no_kv_offload.insert(params.no_kv_offload.end(), p.begin(), p.end());
} else if (arg == "-fa" || arg == "--flash-attn") {
if (++i >= argc) {
invalid_param = true;
break;
}
auto p = split<bool>(argv[i], split_delim);
params.flash_attn.insert(params.flash_attn.end(), p.begin(), p.end());
} else if (arg == "-mmp" || arg == "--mmap") {
if (++i >= argc) {
invalid_param = true;
@ -477,6 +487,7 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
if (params.split_mode.empty()) { params.split_mode = cmd_params_defaults.split_mode; }
if (params.main_gpu.empty()) { params.main_gpu = cmd_params_defaults.main_gpu; }
if (params.no_kv_offload.empty()){ params.no_kv_offload = cmd_params_defaults.no_kv_offload; }
if (params.flash_attn.empty()) { params.flash_attn = cmd_params_defaults.flash_attn; }
if (params.tensor_split.empty()) { params.tensor_split = cmd_params_defaults.tensor_split; }
if (params.use_mmap.empty()) { params.use_mmap = cmd_params_defaults.use_mmap; }
if (params.embeddings.empty()) { params.embeddings = cmd_params_defaults.embeddings; }
@ -498,6 +509,7 @@ struct cmd_params_instance {
llama_split_mode split_mode;
int main_gpu;
bool no_kv_offload;
bool flash_attn;
std::vector<float> tensor_split;
bool use_mmap;
bool embeddings;
@ -532,6 +544,7 @@ struct cmd_params_instance {
cparams.type_k = type_k;
cparams.type_v = type_v;
cparams.offload_kqv = !no_kv_offload;
cparams.flash_attn = flash_attn;
cparams.embeddings = embeddings;
return cparams;
@ -554,6 +567,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
for (const auto & tk : params.type_k)
for (const auto & tv : params.type_v)
for (const auto & nkvo : params.no_kv_offload)
for (const auto & fa : params.flash_attn)
for (const auto & nt : params.n_threads) {
for (const auto & n_prompt : params.n_prompt) {
if (n_prompt == 0) {
@ -572,6 +586,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
/* .split_mode = */ sm,
/* .main_gpu = */ mg,
/* .no_kv_offload= */ nkvo,
/* .flash_attn = */ fa,
/* .tensor_split = */ ts,
/* .use_mmap = */ mmp,
/* .embeddings = */ embd,
@ -596,6 +611,7 @@ static std::vector<cmd_params_instance> get_cmd_params_instances(const cmd_param
/* .split_mode = */ sm,
/* .main_gpu = */ mg,
/* .no_kv_offload= */ nkvo,
/* .flash_attn = */ fa,
/* .tensor_split = */ ts,
/* .use_mmap = */ mmp,
/* .embeddings = */ embd,
@ -633,6 +649,7 @@ struct test {
llama_split_mode split_mode;
int main_gpu;
bool no_kv_offload;
bool flash_attn;
std::vector<float> tensor_split;
bool use_mmap;
bool embeddings;
@ -657,6 +674,7 @@ struct test {
split_mode = inst.split_mode;
main_gpu = inst.main_gpu;
no_kv_offload = inst.no_kv_offload;
flash_attn = inst.flash_attn;
tensor_split = inst.tensor_split;
use_mmap = inst.use_mmap;
embeddings = inst.embeddings;
@ -731,7 +749,7 @@ struct test {
"n_batch", "n_ubatch",
"n_threads", "type_k", "type_v",
"n_gpu_layers", "split_mode",
"main_gpu", "no_kv_offload",
"main_gpu", "no_kv_offload", "flash_attn",
"tensor_split", "use_mmap", "embeddings",
"n_prompt", "n_gen", "test_time",
"avg_ns", "stddev_ns",
@ -753,7 +771,7 @@ struct test {
}
if (field == "cuda" || field == "opencl" || field == "vulkan" || field == "kompute" || field == "metal" ||
field == "gpu_blas" || field == "blas" || field == "sycl" ||field == "f16_kv" || field == "no_kv_offload" ||
field == "use_mmap" || field == "embeddings") {
field == "flash_attn" || field == "use_mmap" || field == "embeddings") {
return BOOL;
}
if (field == "avg_ts" || field == "stddev_ts") {
@ -787,7 +805,7 @@ struct test {
std::to_string(n_batch), std::to_string(n_ubatch),
std::to_string(n_threads), ggml_type_name(type_k), ggml_type_name(type_v),
std::to_string(n_gpu_layers), split_mode_str(split_mode),
std::to_string(main_gpu), std::to_string(no_kv_offload),
std::to_string(main_gpu), std::to_string(no_kv_offload), std::to_string(flash_attn),
tensor_split_str, std::to_string(use_mmap), std::to_string(embeddings),
std::to_string(n_prompt), std::to_string(n_gen), test_time,
std::to_string(avg_ns()), std::to_string(stdev_ns()),
@ -955,6 +973,9 @@ struct markdown_printer : public printer {
if (field == "no_kv_offload") {
return "nkvo";
}
if (field == "flash_attn") {
return "fa";
}
if (field == "use_mmap") {
return "mmap";
}
@ -1001,6 +1022,9 @@ struct markdown_printer : public printer {
if (params.no_kv_offload.size() > 1 || params.no_kv_offload != cmd_params_defaults.no_kv_offload) {
fields.emplace_back("no_kv_offload");
}
if (params.flash_attn.size() > 1 || params.flash_attn != cmd_params_defaults.flash_attn) {
fields.emplace_back("flash_attn");
}
if (params.tensor_split.size() > 1 || params.tensor_split != cmd_params_defaults.tensor_split) {
fields.emplace_back("tensor_split");
}

2
examples/main/README.md
View file

@ -66,7 +66,7 @@ main.exe -m models\7B\ggml-model.bin --ignore-eos -n -1 --random-prompt
In this section, we cover the most commonly used options for running the `main` program with the LLaMA models:
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.bin`).
- `-m FNAME, --model FNAME`: Specify the path to the LLaMA model file (e.g., `models/7B/ggml-model.gguf`; inferred from `--model-url` if set).
- `-mu MODEL_URL --model-url MODEL_URL`: Specify a remote http url to download the file (e.g https://huggingface.co/ggml-org/models/resolve/main/phi-2/ggml-model-q4_0.gguf).
- `-i, --interactive`: Run the program in interactive mode, allowing you to provide input directly and receive real-time responses.
- `-ins, --instruct`: Run the program in instruction mode, which is particularly useful when working with Alpaca models.

2
examples/main/main.cpp
View file

@ -324,7 +324,7 @@ int main(int argc, char ** argv) {
log_tostr(embd_inp.empty()), n_matching_session_tokens, embd_inp.size(), session_tokens.size(), embd_inp.size());
// if we will use the cache for the full prompt without reaching the end of the cache, force
// reevaluation of the last token token to recalculate the cached logits
// reevaluation of the last token to recalculate the cached logits
if (!embd_inp.empty() && n_matching_session_tokens == embd_inp.size() && session_tokens.size() > embd_inp.size()) {
LOGLN("recalculate the cached logits (do): session_tokens.resize( %zu )", embd_inp.size() - 1);

2
examples/quantize-stats/quantize-stats.cpp
View file

@ -23,7 +23,7 @@
#endif
struct quantize_stats_params {
std::string model = "models/7B/ggml-model-f16.gguf";
std::string model = DEFAULT_MODEL_PATH;
bool verbose = false;
bool per_layer_stats = false;
bool print_histogram = false;

1
examples/server/bench/bench.py
View file

@ -268,6 +268,7 @@ def start_server_background(args):
server_args.extend(['--defrag-thold', "0.1"])
server_args.append('--cont-batching')
server_args.append('--metrics')
server_args.append('--flash-attn')
server_args.extend(['--log-format', "text"])
args = [str(arg) for arg in [server_path, *server_args]]
print(f"bench: starting server with: {' '.join(args)}")

7
examples/server/server.cpp
View file

@ -2353,7 +2353,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" disable KV offload\n");
}
printf(" -m FNAME, --model FNAME\n");
printf(" model path (default: %s)\n", params.model.c_str());
printf(" model path (default: models/$filename with filename from --hf-file or --model-url if set, otherwise %s)\n", DEFAULT_MODEL_PATH);
printf(" -mu MODEL_URL, --model-url MODEL_URL\n");
printf(" model download url (default: unused)\n");
printf(" -hfr REPO, --hf-repo REPO\n");
@ -2377,6 +2377,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" --embeddings enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
printf(" -np N, --parallel N number of slots for process requests (default: %d)\n", params.n_parallel);
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: enabled)\n");
printf(" -fa, --flash-attn enable Flash Attention (default: %s)\n", params.flash_attn ? "enabled" : "disabled");
printf(" -spf FNAME, --system-prompt-file FNAME\n");
printf(" set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.\n");
printf(" -ctk TYPE, --cache-type-k TYPE\n");
@ -2742,6 +2743,8 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
params.embedding = true;
} else if (arg == "-cb" || arg == "--cont-batching") {
params.cont_batching = true;
} else if (arg == "-fa" || arg == "--flash-attn") {
params.flash_attn = true;
} else if (arg == "-np" || arg == "--parallel") {
if (++i >= argc) {
invalid_param = true;
@ -2835,6 +2838,8 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
}
}
gpt_params_handle_model_default(params);
if (!params.kv_overrides.empty()) {
params.kv_overrides.emplace_back();
params.kv_overrides.back().key[0] = 0;

2
examples/server/tests/features/embeddings.feature
View file

@ -5,7 +5,7 @@ Feature: llama.cpp server
Background: Server startup
Given a server listening on localhost:8080
And a model url https://huggingface.co/ggml-org/models/resolve/main/bert-bge-small/ggml-model-f16.gguf
And a model file ggml-model-f16.gguf
And a model file bert-bge-small.gguf
And a model alias bert-bge-small
And 42 as server seed
And 2 slots