From 9c67c2773d4b706cf71d70ecf4aa180b62501960 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 30 Apr 2024 12:16:08 +0300 Subject: ggml : add Flash Attention (#5021) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * ggml : add ggml_flash_attn_ext API * ggml : fix GQA support in ggml_flash_attn_ext * ggml : online attention (CPU) * metal : initial implementation * metal : f16 precision * metal : reduce branches * metal : specialize for head size * wip : 8 rows per simd group * wip : 4 rows per simd group * wip : template for rows per warp * metal : parallelize across KV size * metal : parallel reduce across heads * metal : efficient flash_attn_f16 implementation * metal : avoid redundant loads of the attention * metal : scale and mask in matrix form * metal : fix comment * llama : avoid ggml_cast, use F32 query * metal : add parallel reduce version (disabled) * metal : move output into local memory + optimize - the result from each simdgroup now stays in the registers - significantly reduced SRAM usage - more efficient skipping of -INF blocks - avoid simdgroup barrier in hot loop - add comments * metal : add tests, fix scaling, support C > 32 * metal : improve precision * ggml : fix f16 mad * metal : minor * metal : support Q > 8 * tests : add ATTN tests * metal : disable buffer allocation logs * tests : more * metal : faster inner loop for C == 32 * metal : fix array initialization * tests : ifdef * ggml : switch to padded F16 mask for ggml_soft_max, ggml_flash_attn_ext * ggml : fix ggml_soft_max mask requirement * cuda : fix soft_max to use correct mask size * cuda : add flash_attn kernel (wip) * metal : optimize softmax for C > 32 * metal : optimize softmax * tests : minor fix * cuda : avoid zeroing fragments * tests : update dims * cuda : fix __hisinf() result check * cuda : avoid warp_reduce for smax * cuda : use int instead of int64_t Noticeably improves performance (thanks to Johannes) * cuda : make loops use the same loop values Thanks Johannes again for the tip * cuda : unroll some of the loops * cuda : avoid __hisinf branches * cuda : use half2 in softmax * cuda : switch to 1 warp for bs > 16 * cuda : speed-up reduce part of the kernel * cuda : unroll Q*K^T loop * cuda : fix -INF block check * cuda : simplify softmax * cuda : fix matrix names * cuda : minor * llama : adapt to F16 KQ_pos * llama : adapt new models to F16 KQ_mask * ggml : fix F16 store (ARM NEON) * llama : fix type of KQ_mask and KQ_pos * ggml : fix CPU soft_max * tests : add hs=256 * cuda : fix build * metal : improve perf via smaller int registers * cuda : adapt soft_max to F16 mask and pos * CUDA: faster FlashAttention, kernel for bs == 1 * 16 cols for Phi-2 * no vec for hs, no hs==256 ncols==32 for Volta * adjust kernel selection logic * 4 warps, 256 stride for all D * no ncols == 64 * Multiple parallel blocks for batch size 1 * fix compile warnings * fix excessive KQ_b loads * fix cmake build * fix KV cache padding, NaN from INFINITY (#6438) * llama : flash_attn cparam + fix defrag * server: support flash_attn param * server: bench: enable flash_attn param * CUDA: refactor host code, dyn. par. blocks * fix flash_attn_vec_f16 race condition * flush softmax exp below threshold to 0 * store temp KQ in registers * Calculate KQ as FP32 if KQV has GGML_PREC_F32 * Add __hgt2_mask implementation for CUDA 11 * fix KQ FP32 precision fpr parallel_blocks > 1 * llama-bench : add -fa,--flash-attn arg * metal : add BS=1 kernel for flash attention (#6508) * metal : add BS=1 kernel for flash attention (wip) * metal : support more than 1 warps * metal : opts * metal : opt * metal : switch to parallel reduce * metal : reduce registers * metal : simplify * metal : initial FA vec kernel * metal : use F32 attention accumulators * batched-bench : add fattn arg * llama : simplify llama_build_kv_store ggml-ci * llama : adapt build_olmo to changes * ggml : fix arm fp16 store on windows * metal : clean-up * metal : clean-up kernel code * metal : minor * tests : remove benchmarks ggml-ci * ggml : fix avx512 const correctness ggml-ci * ggml : fix soft_max with bias on CPU ggml-ci * common : print --flash-attn in help * ggml : fix num dimensions in ggml_flash_attn_ext * llama : force disable flash attention for incompatible models * ggml : ggml_soft_max support F16/F32 mask/pos ggml-ci * cuda : uint -> uint32_t * cuda : "constexpr dim3" -> "const dim3" ggml-ci * cuda : try to fix __hgt2_mask ggml-ci * ggml : add TODO's for F16/F32 mask/pos support in other backends * llama : replace bool need_kq_pos with use_alibi * llama : prep ALiBi support for BERT models ggml-ci * llama : fix n_batch requirements ggml-ci * cont * server : add help for --flash-attn arg * llama : disable FA for AMD * tests : remove TMP_ATTN_BENCH ggml-ci * llama : support save/load state with FA enabled ggml-ci * ci : add CUDA save-load-state tests ggml-ci * llama : llama_kv_cache_clear zeroes data + fix save-load seq ggml-ci * llama : fix copy-paste errors, add TODO * llama : disallow incompatible states * llama : update llama_state_get_size after v_trans field * metal : remove tmp log * llama : add static reminder for llama_state_get_size * metal : fix max nsg ggml-ci * ci : fix arg order ggml-ci --------- Co-authored-by: Johannes Gäßler Co-authored-by: Pierrick HYMBERT --- examples/batched-bench/batched-bench.cpp | 28 +++++++++++++++++----------- examples/llama-bench/llama-bench.cpp | 30 +++++++++++++++++++++++++++--- examples/server/bench/bench.py | 1 + examples/server/server.cpp | 3 +++ 4 files changed, 48 insertions(+), 14 deletions(-) (limited to 'examples') diff --git a/examples/batched-bench/batched-bench.cpp b/examples/batched-bench/batched-bench.cpp index 1e34de62..2924d811 100644 --- a/examples/batched-bench/batched-bench.cpp +++ b/examples/batched-bench/batched-bench.cpp @@ -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] \n" , argv[0]); + printf("usage: %s MODEL_PATH [N_KV_MAX] [N_BATCH] [N_UBATCH] [FATTN] [IS_PP_SHARED] [NGL] \n" , argv[0]); printf(" , 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"); diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 8b532c8b..95c3095d 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -174,6 +174,7 @@ struct cmd_params { std::vector split_mode; std::vector main_gpu; std::vector no_kv_offload; + std::vector flash_attn; std::vector> tensor_split; std::vector use_mmap; std::vector 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(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 (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str()); printf(" -mg, --main-gpu (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 (default: 0)\n"); @@ -393,6 +396,13 @@ static cmd_params parse_cmd_params(int argc, char ** argv) { } auto p = split(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(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 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 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 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 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 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"); } diff --git a/examples/server/bench/bench.py b/examples/server/bench/bench.py index 6ca637bd..86c5de10 100644 --- a/examples/server/bench/bench.py +++ b/examples/server/bench/bench.py @@ -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)}") diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 01453af2..f60530cf 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -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; -- cgit v1.2.3