File size: 31,006 Bytes
bd503de | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 | #include "ds4.h"
#include "ds4_distributed.h"
#include "ds4_gpu_args.h"
#include "ds4_help.h"
/* Purpose-built throughput benchmark.
*
* The benchmark walks one fixed token sequence to configurable context
* frontiers, measuring only the newest prefill interval at each frontier. It
* then snapshots the live session in memory when the payload is small enough,
* performs a fixed greedy decode run without allowing EOS, restores the
* snapshot or replays the prefix, and continues to the next frontier. Snapshot
* save/restore time is intentionally outside both timing windows.
*/
#include <errno.h>
#include <limits.h>
#include <math.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#define DS4_BENCH_DEFAULT_SNAPSHOT_MAX_BYTES (UINT64_C(1) << 30)
typedef struct {
const char *model_path;
const char *prompt_path;
const char *chat_prompt_path;
const char *system;
const char *csv_path;
const char *expert_profile_path;
const char *gpu_vram_arg;
const char *gpu_devices_arg;
ds4_backend backend;
int threads;
int ctx_start;
int ctx_max;
int ctx_alloc;
int step_incr;
int gen_tokens;
int power_percent;
uint32_t prefill_chunk;
uint32_t ssd_streaming_cache_experts;
uint64_t ssd_streaming_cache_bytes;
uint32_t ssd_streaming_full_layers;
uint32_t ssd_streaming_preload_experts;
uint64_t simulate_used_memory_bytes;
double step_mul;
const char *dump_frontier_logits_dir;
ds4_dist_options dist;
bool warm_weights;
bool quality;
bool ssd_streaming;
bool ssd_streaming_cold;
bool ssd_streaming_full_layers_set;
bool cuda_tensor_parallel;
bool show_output;
} bench_config;
static double bench_now_sec(void) {
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return (double)ts.tv_sec + (double)ts.tv_nsec / 1000000000.0;
}
static uint64_t bench_snapshot_max_bytes(void) {
const char *env = getenv("DS4_BENCH_SNAPSHOT_MAX_BYTES");
if (!env || env[0] == '\0') return DS4_BENCH_DEFAULT_SNAPSHOT_MAX_BYTES;
if (!strcmp(env, "unlimited") || !strcmp(env, "UNLIMITED") ||
!strcmp(env, "inf") || !strcmp(env, "INF")) {
return UINT64_MAX;
}
char *end = NULL;
unsigned long long v = strtoull(env, &end, 10);
if (env[0] == '\0' || !end || *end != '\0') {
fprintf(stderr,
"ds4-bench: invalid DS4_BENCH_SNAPSHOT_MAX_BYTES=%s; using default %llu\n",
env,
(unsigned long long)DS4_BENCH_DEFAULT_SNAPSHOT_MAX_BYTES);
return DS4_BENCH_DEFAULT_SNAPSHOT_MAX_BYTES;
}
return (uint64_t)v;
}
static double bytes_to_gib(uint64_t bytes) {
return (double)bytes / (1024.0 * 1024.0 * 1024.0);
}
static void usage(FILE *fp, const char *topic) {
ds4_help_print(fp, DS4_HELP_BENCH, topic);
}
static int parse_int(const char *s, const char *opt) {
char *end = NULL;
long v = strtol(s, &end, 10);
if (s[0] == '\0' || *end != '\0' || v <= 0 || v > INT_MAX) {
fprintf(stderr, "ds4-bench: invalid value for %s: %s\n", opt, s);
exit(2);
}
return (int)v;
}
static int parse_nonnegative_int(const char *s, const char *opt) {
char *end = NULL;
long v = strtol(s, &end, 10);
if (s[0] == '\0' || *end != '\0' || v < 0 || v > INT_MAX) {
fprintf(stderr, "ds4-bench: invalid value for %s: %s\n", opt, s);
exit(2);
}
return (int)v;
}
static double parse_double_arg(const char *s, const char *opt) {
char *end = NULL;
double v = strtod(s, &end);
if (s[0] == '\0' || *end != '\0' || !isfinite(v)) {
fprintf(stderr, "ds4-bench: invalid value for %s: %s\n", opt, s);
exit(2);
}
return v;
}
static const char *need_arg(int *i, int argc, char **argv, const char *opt) {
if (*i + 1 >= argc) {
fprintf(stderr, "ds4-bench: %s requires an argument\n", opt);
exit(2);
}
return argv[++*i];
}
static ds4_backend parse_backend(const char *s, const char *opt) {
if (!strcmp(s, "metal")) return DS4_BACKEND_METAL;
#ifdef DS4_ROCM_BUILD
if (!strcmp(s, "rocm")) return DS4_BACKEND_CUDA;
#else
if (!strcmp(s, "cuda")) return DS4_BACKEND_CUDA;
#endif
if (!strcmp(s, "cpu")) return DS4_BACKEND_CPU;
fprintf(stderr, "ds4-bench: invalid value for %s: %s\n", opt, s);
#ifdef DS4_ROCM_BUILD
fprintf(stderr, "ds4-bench: valid backends are: metal, rocm, cpu\n");
#else
fprintf(stderr, "ds4-bench: valid backends are: metal, cuda, cpu\n");
#endif
exit(2);
}
static ds4_backend default_backend(void) {
#ifdef DS4_NO_GPU
return DS4_BACKEND_CPU;
#elif defined(__APPLE__)
return DS4_BACKEND_METAL;
#else
return DS4_BACKEND_CUDA;
#endif
}
static char *read_file(const char *path) {
FILE *fp = fopen(path, "rb");
if (!fp) {
fprintf(stderr, "ds4-bench: failed to open %s: %s\n", path, strerror(errno));
exit(1);
}
if (fseek(fp, 0, SEEK_END) != 0) {
fprintf(stderr, "ds4-bench: failed to seek %s\n", path);
fclose(fp);
exit(1);
}
long n = ftell(fp);
if (n < 0) {
fprintf(stderr, "ds4-bench: failed to tell %s\n", path);
fclose(fp);
exit(1);
}
if (fseek(fp, 0, SEEK_SET) != 0) {
fprintf(stderr, "ds4-bench: failed to rewind %s\n", path);
fclose(fp);
exit(1);
}
char *buf = malloc((size_t)n + 1);
if (!buf) {
fprintf(stderr, "ds4-bench: out of memory reading %s\n", path);
fclose(fp);
exit(1);
}
if (fread(buf, 1, (size_t)n, fp) != (size_t)n) {
fprintf(stderr, "ds4-bench: failed to read %s\n", path);
free(buf);
fclose(fp);
exit(1);
}
fclose(fp);
buf[n] = '\0';
return buf;
}
static bench_config parse_options(int argc, char **argv) {
bench_config c = {
.model_path = "ds4flash.gguf",
.system = "You are a helpful assistant.",
.backend = default_backend(),
.ctx_start = 2048,
.ctx_max = 32768,
.step_incr = 2048,
.gen_tokens = 128,
.step_mul = 1.0,
};
for (int i = 1; i < argc; i++) {
const char *arg = argv[i];
if (!strcmp(arg, "-h") || !strcmp(arg, "--help")) {
const char *topic = (i + 1 < argc && argv[i + 1][0] != '-') ?
argv[i + 1] : NULL;
usage(stdout, topic);
exit(0);
}
char dist_parse_err[256] = {0};
ds4_dist_cli_parse_result dist_parse =
ds4_dist_parse_cli_arg(arg,
&i,
argc,
argv,
&c.dist,
dist_parse_err,
sizeof(dist_parse_err));
if (dist_parse == DS4_DIST_CLI_ERROR) {
fprintf(stderr,
"ds4-bench: %s\n",
dist_parse_err[0] ? dist_parse_err : "invalid distributed option");
exit(2);
}
if (dist_parse == DS4_DIST_CLI_MATCHED) continue;
if (!strcmp(arg, "-m") || !strcmp(arg, "--model")) {
c.model_path = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--prompt-file")) {
c.prompt_path = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--chat-prompt-file")) {
c.chat_prompt_path = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "-sys") || !strcmp(arg, "--system")) {
c.system = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--ctx-start")) {
c.ctx_start = parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--ctx-max")) {
c.ctx_max = parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--ctx-alloc")) {
c.ctx_alloc = parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--step-incr")) {
c.step_incr = parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--step-mul")) {
c.step_mul = parse_double_arg(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--gen-tokens") || !strcmp(arg, "--tokens") || !strcmp(arg, "-n")) {
c.gen_tokens = parse_nonnegative_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--csv")) {
c.csv_path = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--dump-frontier-logits-dir")) {
c.dump_frontier_logits_dir = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--expert-profile")) {
c.expert_profile_path = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "-t") || !strcmp(arg, "--threads")) {
c.threads = parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--backend")) {
c.backend = parse_backend(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--metal")) {
c.backend = DS4_BACKEND_METAL;
#ifdef DS4_ROCM_BUILD
} else if (!strcmp(arg, "--rocm")) {
c.backend = DS4_BACKEND_CUDA;
#else
} else if (!strcmp(arg, "--cuda")) {
c.backend = DS4_BACKEND_CUDA;
#endif
} else if (!strcmp(arg, "--gpu-vram")) {
c.gpu_vram_arg = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--gpu-devices")) {
c.gpu_devices_arg = need_arg(&i, argc, argv, arg);
} else if (!strcmp(arg, "--cuda-tensor-parallel")) {
c.cuda_tensor_parallel = true;
} else if (!strcmp(arg, "--cpu")) {
c.backend = DS4_BACKEND_CPU;
} else if (!strcmp(arg, "--quality")) {
c.quality = true;
} else if (!strcmp(arg, "--ssd-streaming")) {
c.ssd_streaming = true;
} else if (!strcmp(arg, "--ssd-streaming-cold")) {
c.ssd_streaming_cold = true;
} else if (!strcmp(arg, "--ssd-streaming-cache-experts")) {
uint32_t experts = 0;
uint64_t bytes = 0;
if (!ds4_parse_streaming_cache_experts_arg(
need_arg(&i, argc, argv, arg), &experts, &bytes)) {
fprintf(stderr,
"ds4-bench: --ssd-streaming-cache-experts must be a positive count or <number>GB\n");
exit(2);
}
c.ssd_streaming_cache_experts = experts;
c.ssd_streaming_cache_bytes = bytes;
} else if (!strcmp(arg, "--ssd-streaming-full-layers")) {
int v = parse_nonnegative_int(need_arg(&i, argc, argv, arg), arg);
c.ssd_streaming_full_layers = (uint32_t)v;
c.ssd_streaming_full_layers_set = true;
} else if (!strcmp(arg, "--ssd-streaming-preload-experts")) {
int v = parse_int(need_arg(&i, argc, argv, arg), arg);
if (v <= 0) {
fprintf(stderr, "ds4-bench: --ssd-streaming-preload-experts must be positive\n");
exit(2);
}
c.ssd_streaming_preload_experts = (uint32_t)v;
} else if (!strcmp(arg, "--simulate-used-memory")) {
if (!ds4_parse_gib_arg(need_arg(&i, argc, argv, arg),
&c.simulate_used_memory_bytes)) {
fprintf(stderr,
"ds4-bench: --simulate-used-memory must be a positive GiB value, e.g. 64GB\n");
exit(2);
}
} else if (!strcmp(arg, "--prefill-chunk")) {
c.prefill_chunk = (uint32_t)parse_int(need_arg(&i, argc, argv, arg), arg);
} else if (!strcmp(arg, "--power")) {
c.power_percent = parse_int(need_arg(&i, argc, argv, arg), arg);
if (c.power_percent < 1 || c.power_percent > 100) {
fprintf(stderr, "ds4-bench: --power must be between 1 and 100\n");
exit(2);
}
} else if (!strcmp(arg, "--warm-weights")) {
c.warm_weights = true;
} else if (!strcmp(arg, "--show-output")) {
c.show_output = true;
} else {
fprintf(stderr, "ds4-bench: unknown option: %s\n", arg);
usage(stderr, NULL);
exit(2);
}
}
if (!!c.prompt_path == !!c.chat_prompt_path) {
fprintf(stderr, "ds4-bench: specify exactly one of --prompt-file or --chat-prompt-file\n");
exit(2);
}
if (c.ctx_start > c.ctx_max) {
fprintf(stderr, "ds4-bench: --ctx-start must be <= --ctx-max\n");
exit(2);
}
if (c.step_mul < 1.0) {
fprintf(stderr, "ds4-bench: --step-mul must be >= 1\n");
exit(2);
}
if (c.step_mul == 1.0 && c.step_incr <= 0) {
fprintf(stderr, "ds4-bench: --step-incr must be positive when --step-mul is 1\n");
exit(2);
}
if (c.ctx_max > INT_MAX - c.gen_tokens - 1) {
fprintf(stderr, "ds4-bench: requested context is too large\n");
exit(2);
}
if (c.ctx_alloc == 0) c.ctx_alloc = c.ctx_max + c.gen_tokens + 1;
if (c.ctx_alloc <= c.ctx_max + c.gen_tokens) {
fprintf(stderr, "ds4-bench: --ctx-alloc must be greater than ctx-max + gen-tokens\n");
exit(2);
}
char dist_err[256];
if (ds4_dist_prepare_engine_options(&c.dist, NULL, dist_err, sizeof(dist_err)) != 0) {
fprintf(stderr, "ds4-bench: %s\n", dist_err);
exit(2);
}
if (c.dist.role == DS4_DISTRIBUTED_WORKER) {
fprintf(stderr, "ds4-bench: --role worker is a serving mode; start workers with ./ds4\n");
exit(2);
}
return c;
}
static void json_write_string(FILE *fp, const char *s) {
fputc('"', fp);
if (s) {
for (const unsigned char *p = (const unsigned char *)s; *p; p++) {
switch (*p) {
case '"': fputs("\\\"", fp); break;
case '\\': fputs("\\\\", fp); break;
case '\b': fputs("\\b", fp); break;
case '\f': fputs("\\f", fp); break;
case '\n': fputs("\\n", fp); break;
case '\r': fputs("\\r", fp); break;
case '\t': fputs("\\t", fp); break;
default:
if (*p < 0x20) fprintf(fp, "\\u%04x", (unsigned)*p);
else fputc((char)*p, fp);
break;
}
}
}
fputc('"', fp);
}
static int write_frontier_logits_json(
const bench_config *cfg,
ds4_engine *engine,
ds4_session *session,
int frontier,
int previous) {
if (!cfg->dump_frontier_logits_dir) return 0;
const int vocab = ds4_engine_vocab_size(engine);
float *logits = malloc((size_t)vocab * sizeof(logits[0]));
if (!logits) {
fprintf(stderr, "ds4-bench: out of memory copying frontier logits\n");
return 1;
}
if (ds4_session_copy_logits(session, logits, vocab) != vocab) {
fprintf(stderr, "ds4-bench: failed to copy frontier logits at %d\n", frontier);
free(logits);
return 1;
}
char path[PATH_MAX];
const int n = snprintf(path,
sizeof(path),
"%s/frontier_%06d.logits.json",
cfg->dump_frontier_logits_dir,
frontier);
if (n <= 0 || (size_t)n >= sizeof(path)) {
fprintf(stderr, "ds4-bench: frontier logits path is too long\n");
free(logits);
return 1;
}
FILE *fp = fopen(path, "wb");
if (!fp) {
fprintf(stderr, "ds4-bench: failed to open %s: %s\n", path, strerror(errno));
free(logits);
return 1;
}
const int argmax = ds4_session_argmax(session);
fprintf(fp, "{\n \"source\":\"ds4-bench\",\n \"model\":");
json_write_string(fp, cfg->model_path);
fprintf(fp,
",\n \"backend\":\"%s\",\n \"quality\":%s,\n"
" \"quant_bits\":%d,\n \"prompt_tokens\":%d,\n"
" \"frontier_tokens\":%d,\n \"prefill_tokens\":%d,\n"
" \"ctx\":%d,\n \"vocab\":%d,\n"
" \"argmax_id\":%d,\n \"argmax_logit\":%.9g,\n \"logits\":[",
ds4_backend_name(cfg->backend),
cfg->quality ? "true" : "false",
ds4_engine_routed_quant_bits(engine),
frontier,
frontier,
frontier - previous,
cfg->ctx_alloc,
vocab,
argmax,
logits[argmax]);
for (int i = 0; i < vocab; i++) {
if (i) fputc(',', fp);
if ((i % 8) == 0) fputs("\n ", fp);
if (isfinite(logits[i])) fprintf(fp, "%.9g", logits[i]);
else fputs("null", fp);
}
fputs("\n ]\n}\n", fp);
if (fclose(fp) != 0) {
fprintf(stderr, "ds4-bench: failed to close %s\n", path);
free(logits);
return 1;
}
free(logits);
return 0;
}
static int next_frontier(const bench_config *c, int cur) {
if (cur >= c->ctx_max) return c->ctx_max;
int next;
if (c->step_mul == 1.0) {
if (cur > INT_MAX - c->step_incr) next = c->ctx_max;
else next = cur + c->step_incr;
} else {
const double v = ceil((double)cur * c->step_mul);
next = v > (double)INT_MAX ? c->ctx_max : (int)v;
if (next <= cur) next = cur + 1;
}
if (next > c->ctx_max) next = c->ctx_max;
return next;
}
static void log_context_memory(ds4_backend backend,
int ctx_size,
uint32_t prefill_chunk,
bool ssd_streaming) {
ds4_context_memory m =
ds4_context_memory_estimate_with_prefill_mode(backend,
ctx_size,
prefill_chunk,
ssd_streaming);
fprintf(stderr,
"ds4-bench: context buffers %.2f MiB (ctx=%d, backend=%s, prefill_chunk=%u, raw_kv_rows=%u, compressed_kv_rows=%u)\n",
(double)m.total_bytes / (1024.0 * 1024.0),
ctx_size,
ds4_backend_name(backend),
m.prefill_cap,
m.raw_cap,
m.comp_cap);
}
static int wait_distributed_route(ds4_session *session) {
char err[256] = {0};
char last[256] = {0};
unsigned ticks = 0;
const struct timespec delay = {0, 250000000L};
for (;;) {
int ready = ds4_session_distributed_route_ready(session, err, sizeof(err));
if (ready > 0) {
if (ticks) fprintf(stderr, "ds4-bench: distributed route ready\n");
return 0;
}
if (ready < 0) {
fprintf(stderr,
"ds4-bench: distributed route readiness failed: %s\n",
err[0] ? err : "unknown error");
return 1;
}
const char *why = err[0] ? err : "route incomplete";
if (strcmp(last, why) != 0 || (ticks % 20u) == 0) {
fprintf(stderr, "ds4-bench: waiting for distributed route: %s\n", why);
snprintf(last, sizeof(last), "%s", why);
}
nanosleep(&delay, NULL);
ticks++;
}
}
static void maybe_warn_distributed_step_shape(const bench_config *cfg, ds4_session *session) {
if (!cfg || !session || cfg->dist.role != DS4_DISTRIBUTED_COORDINATOR) return;
uint32_t chunk = cfg->dist.prefill_chunk;
if (chunk == 0) {
const int cap = ds4_session_prefill_cap(session);
if (cap > 0) chunk = (uint32_t)cap;
}
if (chunk == 0) return;
if (cfg->step_mul == 1.0 &&
cfg->step_incr > 0 &&
(uint32_t)cfg->step_incr < chunk &&
cfg->ctx_start < cfg->ctx_max)
{
fprintf(stderr,
"ds4-bench: note: --step-incr=%d is smaller than distributed prefill chunk %u; "
"suffix rows will not show multi-chunk pipeline overlap\n",
cfg->step_incr,
chunk);
}
}
int main(int argc, char **argv) {
bench_config cfg = parse_options(argc, argv);
/* Hint the packer at the largest ctx this bench run will exercise
* so per-layer KV bytes are priced for the real session size, not
* a stale 4096 default. Single-tier and CPU paths ignore this. */
int placement_ctx_hint = cfg.ctx_max;
if (cfg.ctx_alloc > placement_ctx_hint) placement_ctx_hint = cfg.ctx_alloc;
ds4_gpu_config gpu_cfg = {0};
bool skip_cuda = false;
const bool have_gpu_config = cfg.gpu_vram_arg || cfg.gpu_devices_arg;
if (have_gpu_config) {
char gpu_err[256];
if (parse_gpu_vram_arg(cfg.gpu_vram_arg, cfg.gpu_devices_arg,
&gpu_cfg, &skip_cuda,
gpu_err, sizeof(gpu_err)) != 0) {
fprintf(stderr, "ds4-bench: %s\n", gpu_err);
return 2;
}
cfg.backend = skip_cuda ? DS4_BACKEND_CPU : DS4_BACKEND_CUDA;
}
ds4_engine_options opt = {
.model_path = cfg.model_path,
.backend = cfg.backend,
.n_threads = cfg.threads,
.context_size = cfg.ctx_alloc,
.prefill_chunk = cfg.prefill_chunk,
.ssd_streaming_cache_experts = cfg.ssd_streaming_cache_experts,
.ssd_streaming_cache_bytes = cfg.ssd_streaming_cache_bytes,
.ssd_streaming_full_layers = cfg.ssd_streaming_full_layers,
.ssd_streaming_preload_experts = cfg.ssd_streaming_preload_experts,
.simulate_used_memory_bytes = cfg.simulate_used_memory_bytes,
.power_percent = cfg.power_percent,
.warm_weights = cfg.warm_weights,
.quality = cfg.quality,
.cuda_tensor_parallel = cfg.cuda_tensor_parallel,
.ssd_streaming = cfg.ssd_streaming,
.ssd_streaming_cold = cfg.ssd_streaming_cold,
.ssd_streaming_full_layers_set = cfg.ssd_streaming_full_layers_set,
.expert_profile_path = cfg.expert_profile_path,
.distributed = cfg.dist,
};
char dist_err[256];
if (ds4_dist_prepare_engine_options(&cfg.dist, &opt, dist_err, sizeof(dist_err)) != 0) {
fprintf(stderr, "ds4-bench: %s\n", dist_err);
return 2;
}
ds4_engine *engine = NULL;
if (have_gpu_config && !skip_cuda) {
const bool was_auto =
(cfg.gpu_vram_arg && !strcmp(cfg.gpu_vram_arg, "auto")) ||
(!cfg.gpu_vram_arg && cfg.gpu_devices_arg);
char layout[256];
if (format_gpu_layout_line(&gpu_cfg, was_auto,
layout, sizeof(layout)) > 0) {
fprintf(stdout, "%s\n", layout);
fflush(stdout);
}
if (ds4_engine_create_with_gpu_config(
&engine, &opt, &gpu_cfg) != 0) return 1;
} else if (ds4_engine_open(&engine, &opt) != 0) {
return 1;
}
log_context_memory(opt.backend,
cfg.ctx_alloc,
ds4_engine_prefill_chunk(engine),
cfg.ssd_streaming);
char *text = read_file(cfg.prompt_path ? cfg.prompt_path : cfg.chat_prompt_path);
ds4_tokens prompt = {0};
if (cfg.chat_prompt_path) {
ds4_encode_chat_prompt(engine, cfg.system, text, DS4_THINK_NONE, &prompt);
} else {
ds4_tokenize_text(engine, text, &prompt);
}
free(text);
if (prompt.len < cfg.ctx_max) {
fprintf(stderr,
"ds4-bench: prompt has %d tokens, need at least --ctx-max=%d\n",
prompt.len,
cfg.ctx_max);
ds4_tokens_free(&prompt);
ds4_engine_close(engine);
return 1;
}
ds4_session *session = NULL;
if (ds4_session_create(&session, engine, cfg.ctx_alloc) != 0) {
fprintf(stderr, "ds4-bench: failed to create session\n");
ds4_tokens_free(&prompt);
ds4_engine_close(engine);
return 1;
}
if (cfg.dist.role == DS4_DISTRIBUTED_COORDINATOR &&
wait_distributed_route(session) != 0)
{
ds4_session_free(session);
ds4_tokens_free(&prompt);
ds4_engine_close(engine);
return 1;
}
maybe_warn_distributed_step_shape(&cfg, session);
FILE *out = stdout;
if (cfg.csv_path) {
out = fopen(cfg.csv_path, "wb");
if (!out) {
fprintf(stderr, "ds4-bench: failed to open %s: %s\n", cfg.csv_path, strerror(errno));
ds4_session_free(session);
ds4_tokens_free(&prompt);
ds4_engine_close(engine);
return 1;
}
}
fprintf(out, "ctx_tokens,prefill_tokens,prefill_tps,gen_tokens,gen_tps,gen_first_ms,gen_steady_tokens,gen_steady_tps,kvcache_bytes\n");
fflush(out);
const int eos = ds4_token_eos(engine);
const bool distributed = cfg.dist.role == DS4_DISTRIBUTED_COORDINATOR;
ds4_session_snapshot snap = {0};
const uint64_t snapshot_max_bytes = bench_snapshot_max_bytes();
bool warned_large_snapshot = false;
char err[256];
int previous = 0;
int rc = 0;
for (int frontier = cfg.ctx_start; ; frontier = next_frontier(&cfg, frontier)) {
ds4_tokens prefix = {
.v = prompt.v,
.len = frontier,
.cap = frontier,
};
const double prefill_t0 = bench_now_sec();
if (ds4_session_sync(session, &prefix, err, sizeof(err)) != 0) {
fprintf(stderr, "ds4-bench: prefill to %d failed: %s\n", frontier, err);
rc = 1;
break;
}
const double prefill_t1 = bench_now_sec();
const double prefill_sec = prefill_t1 - prefill_t0;
const int prefill_tokens = frontier - previous;
if (write_frontier_logits_json(&cfg, engine, session, frontier, previous) != 0) {
rc = 1;
break;
}
const bool need_restore_after_generation =
cfg.gen_tokens > 0 && frontier < cfg.ctx_max;
bool have_snapshot = false;
if (need_restore_after_generation && !distributed &&
getenv("DS4_BENCH_DISABLE_SNAPSHOT") == NULL) {
const uint64_t payload_bytes = ds4_session_payload_bytes(session);
const bool large_snapshot_forced =
getenv("DS4_BENCH_FORCE_SNAPSHOT") != NULL;
if (payload_bytes > snapshot_max_bytes && !large_snapshot_forced) {
if (!warned_large_snapshot) {
fprintf(stderr,
"ds4-bench: session payload snapshot is %.2f GiB, above the %.2f GiB benchmark limit; "
"replaying prefixes instead (set DS4_BENCH_FORCE_SNAPSHOT=1 to force snapshots)\n",
bytes_to_gib(payload_bytes),
bytes_to_gib(snapshot_max_bytes));
warned_large_snapshot = true;
}
} else if (payload_bytes > 0) {
if (ds4_session_save_snapshot(session, &snap, err, sizeof(err)) != 0) {
fprintf(stderr, "ds4-bench: snapshot at %d failed: %s\n", frontier, err);
rc = 1;
break;
}
have_snapshot = true;
}
}
const double gen_t0 = bench_now_sec();
double gen_first_sec = 0.0;
double gen_steady_sec = 0.0;
int gen_done = 0;
int *gen_token_buf = cfg.show_output && cfg.gen_tokens > 0
? malloc((size_t)cfg.gen_tokens * sizeof(gen_token_buf[0]))
: NULL;
int gen_token_count = 0;
for (int i = 0; i < cfg.gen_tokens; i++) {
if (ds4_session_pos(session) + 1 >= ds4_session_ctx(session)) {
fprintf(stderr, "ds4-bench: generation would exceed allocated context at frontier %d\n", frontier);
rc = 1;
break;
}
const int token = ds4_session_argmax_excluding(session, eos);
if (token < 0) {
fprintf(stderr, "ds4-bench: failed to choose non-EOS token at frontier %d\n", frontier);
rc = 1;
break;
}
const double token_t0 = bench_now_sec();
if (ds4_session_eval(session, token, err, sizeof(err)) != 0) {
fprintf(stderr, "ds4-bench: decode at frontier %d failed: %s\n", frontier, err);
rc = 1;
break;
}
const double token_t1 = bench_now_sec();
if (i == 0) gen_first_sec = token_t1 - token_t0;
else gen_steady_sec += token_t1 - token_t0;
if (gen_token_buf) gen_token_buf[gen_token_count++] = token;
gen_done++;
}
const double gen_t1 = bench_now_sec();
if (cfg.show_output && gen_token_buf && gen_token_count > 0) {
fprintf(stderr, "ds4-bench: gen[ctx=%d] decoded text: \"", frontier);
for (int i = 0; i < gen_token_count; i++) {
size_t tlen = 0;
char *txt = ds4_token_text(engine, gen_token_buf[i], &tlen);
if (txt) {
fwrite(txt, 1, tlen, stderr);
free(txt);
}
}
fprintf(stderr, "\"\n");
fflush(stderr);
}
free(gen_token_buf);
if (rc != 0) break;
if (!need_restore_after_generation) {
/* Nothing later depends on the frontier state. */
} else if (distributed || !have_snapshot) {
if (ds4_session_sync(session, &prefix, err, sizeof(err)) != 0) {
fprintf(stderr, "ds4-bench: replay restore at %d failed: %s\n", frontier, err);
rc = 1;
break;
}
} else {
if (ds4_session_load_snapshot(session, &snap, err, sizeof(err)) != 0) {
fprintf(stderr, "ds4-bench: restore at %d failed: %s\n", frontier, err);
rc = 1;
break;
}
}
const double gen_sec = gen_t1 - gen_t0;
const int gen_steady_tokens = gen_done > 1 ? gen_done - 1 : 0;
fprintf(out,
"%d,%d,%.2f,%d,%.2f,%.3f,%d,%.2f,%llu\n",
frontier,
prefill_tokens,
prefill_sec > 0.0 ? (double)prefill_tokens / prefill_sec : 0.0,
gen_done,
gen_sec > 0.0 ? (double)gen_done / gen_sec : 0.0,
gen_first_sec * 1000.0,
gen_steady_tokens,
gen_steady_sec > 0.0 ? (double)gen_steady_tokens / gen_steady_sec : 0.0,
(unsigned long long)(have_snapshot ? snap.len : 0));
fflush(out);
previous = frontier;
if (frontier >= cfg.ctx_max) break;
}
if (out != stdout) fclose(out);
ds4_session_snapshot_free(&snap);
ds4_session_free(session);
ds4_tokens_free(&prompt);
ds4_engine_close(engine);
return rc;
}
|