/* Motore di inferenza OLMoE in C puro, con EXPERT-STREAMING dal disco. * Porting del motore Python (engine.py). Obiettivo Stadio A: produrre gli STESSI * token id del riferimento (ref.json) -> valida il core prima di scalare a GLM-5.2. * * Densa (embed, attn, router, norme, lm_head) residente in RAM (float32). * Expert letti dal disco on-demand via pread+fadvise(DONTNEED), cache LRU per-layer. * Matmul multi-thread con OpenMP (niente BLAS). * * ENV VARS: * PILOT=0/1/2/3 : 0=no prefetch, 1=1-layer lookahead, 2=2-layer, 3=3-layer lookahead * HOT=N : pin top-N hot experts per layer permanently (never evict) * WARMUP=N : tokens before hot pinning activates (default 5) * WIDE=N : prefetch top-K*N candidates (default 1, try 2 or 3) * SMOOTH=F : EMA coefficient for routing momentum (default 0.3, range 0.0-0.95) * CONF_LIMIT=F : cumulative gate probability threshold for prefetch cutoff (default 0.92) * (expert queue is sorted by eid for SSD read locality) */ #define _GNU_SOURCE #include #include #include #include #include #include #if defined(__APPLE__) || defined(__linux__) || defined(__FreeBSD__) #include #include #endif #include "st.h" #ifdef _WIN32 #include #define sleep_ms(ms) Sleep(ms) #else #define sleep_ms(ms) usleep((ms) * 1000) #endif /* ---------- config ---------- */ typedef struct { int hidden, n_layers, n_heads, n_kv_heads, head_dim; int n_experts, topk, inter, vocab; float theta, eps; int norm_topk; } Cfg; /* ---------- pesi densi per-layer ---------- */ typedef struct { float *in_ln, *post_ln, *q, *k, *v, *o, *qn, *kn, *gate; } Layer; /* ---------- cache LRU degli expert (pesi QUANTIZZATI) ---------- * Ogni weight [out,in] tenuto come int8 (per-riga) + scala float per riga. * Cosi' la RAM-cache scende da 4 byte/param (f32) a 1 byte/param: e' il * meccanismo che fa stare GLM-5.2 nei 15 GB. dequant-on-use nel matmul. */ /* IMPROVEMENT 2: pinned=1 means this slot is never evicted (hot expert). */ typedef struct { int eid; int pinned; int8_t *g, *u, *d; float *gs, *us, *ds; uint64_t used; } Slot; typedef struct { Slot *slots; int n, cap; } LCache; typedef struct { Cfg c; shards S; int quant_bits; float *embed, *lm_head, *final_norm; Layer *L; LCache *cache; /* [n_layers] */ uint64_t clock, hits, miss; float **K, **V; int kv_len, max_t; double dense_load_s; /* IMPROVEMENT 2: expert frequency heatmap */ uint32_t *freq; int freq_token_count, hot_pinned, hot_n, warmup_tokens; int token_count; /* PREDICTION IMPROVEMENT A: per-layer smoothed gate logits across tokens. * momentum_logits[l*E .. (l+1)*E-1] = EMA of recent gate outputs. * Blended with fresh gate prediction: final = (1-smooth)*fresh + smooth*ema. * Captures routing consistency across tokens (same token tends to reuse experts). */ float *momentum_logits; /* [n_layers * n_experts], EMA of gate logits */ float pilot_smooth; /* SMOOTH env: EMA coefficient 0.0-0.9 (default 0.3) */ uint8_t *is_pinned; /* [n_layers * n_experts], 1 if expert is globally pinned */ uint8_t *is_queued; /* [n_layers * n_experts], 1 if expert is currently in the prefetch queue */ float pilot_conf_limit; /* CONF_LIMIT env: cumulative gate probability threshold (e.g. 0.92) */ } Model; static pthread_mutex_t g_pilot_mx = PTHREAD_MUTEX_INITIALIZER; static struct { int l, e; } pilot_q[4096]; static volatile unsigned pilot_r = 0, pilot_w = 0; static Model *pilot_m = NULL; static int g_pilot = 0; static int g_wide = 1; /* IMPROVEMENT 4: top-K * g_wide candidates prefetched */ static void pilot_prefetch(Model *m, int lnext, const float *x, int S); static void *pilot_worker(void *arg); static void ensure_pilot_worker_started(Model *m); static void slot_ensure_allocated(Model *m, Slot *s); static void ensure_pilot_worker_started(Model *m) { if (!pilot_m) { pilot_m = m; pthread_t t; if (pthread_create(&t, NULL, pilot_worker, NULL) != 0) { fprintf(stderr, "Error: Failed to create pilot prefetch worker thread\n"); exit(1); } pthread_detach(t); } } /* ---------- utility ---------- */ static double now_s(void) { struct timespec t; clock_gettime(CLOCK_MONOTONIC, &t); return t.tv_sec + t.tv_nsec*1e-9; } #if defined(__APPLE__) static double rss_gb(void) { struct rusage r; getrusage(RUSAGE_SELF, &r); return r.ru_maxrss / (1024.0*1024.0*1024.0); } /* macOS: byte */ #else static double rss_gb(void) { struct rusage r; getrusage(RUSAGE_SELF, &r); return r.ru_maxrss / (1024.0*1024.0); } /* Linux: KB */ #endif static float *falloc(int64_t n) { float *p = malloc(n*sizeof(float)); if(!p){fprintf(stderr,"OOM %ld\n",(long)n);exit(1);} return p; } /* y[S,O] = x[S,I] @ W^T, W e' [O,I] row-major */ static void matmul(float *y, const float *x, const float *W, int S, int I, int O) { #pragma omp parallel for schedule(static) for (int o = 0; o < O; o++) { const float *w = W + (int64_t)o * I; for (int s = 0; s < S; s++) { const float *xs = x + (int64_t)s * I; float acc = 0.f; for (int i = 0; i < I; i++) acc += xs[i] * w[i]; y[(int64_t)s * O + o] = acc; } } } /* y[1,O] = x[1,I] @ W^T con W quantizzato: q[O,I] int8 + scala per riga. * W[o,i] ~= q[o,i]*scale[o] -> y[o] = scale[o] * sum_i x[i]*q[o,i]. * Su ARM: attivazione quantizzata Q8_0 (scala per blocco di 16) + dot int8 * NEON (sdot dove c'e' dotprod) — stessa famiglia IDOT di glm.c, IDOT=0 per * la via scalare byte-esatta. Misurato 2.7x end-to-end su M5. */ #if defined(__ARM_NEON) #include static inline int32_t dot_i8_16(const int8_t *a, const int8_t *b) { int32x4_t acc = vdupq_n_s32(0); int8x16_t va = vld1q_s8(a), vb = vld1q_s8(b); #if defined(__ARM_FEATURE_DOTPROD) acc = vdotq_s32(acc, va, vb); #else acc = vpadalq_s16(acc, vmull_s8(vget_low_s8(va), vget_low_s8(vb))); acc = vpadalq_s16(acc, vmull_s8(vget_high_s8(va), vget_high_s8(vb))); #endif return vaddvq_s32(acc); } #endif static void matmul_q(float *y, const float *x, const int8_t *q, const float *scale, int I, int O) { #if defined(__ARM_NEON) static int idot = -1; if (idot < 0) { const char *e = getenv("IDOT"); idot = !(e && *e == '0'); } if (idot && I % 16 == 0 && I <= 4096) { int nb = I / 16; int8_t xi[4096]; float xs[256]; for (int b = 0; b < nb; b++) { const float *xb = x + b*16; float am = 0.f; for (int i = 0; i < 16; i++) { float a = fabsf(xb[i]); if (a > am) am = a; } float s = am/127.f; if (s < 1e-12f) s = 1e-12f; xs[b] = s; float inv = 1.f/s; for (int i = 0; i < 16; i++) xi[b*16+i] = (int8_t)lrintf(xb[i]*inv); } #pragma omp parallel for schedule(static) for (int o = 0; o < O; o++) { const int8_t *w = q + (int64_t)o * I; float acc = 0.f; for (int b = 0; b < nb; b++) acc += xs[b]*(float)dot_i8_16(xi+b*16, w+b*16); y[o] = acc * scale[o]; } return; } #endif #pragma omp parallel for schedule(static) for (int o = 0; o < O; o++) { const int8_t *w = q + (int64_t)o * I; float acc = 0.f; for (int i = 0; i < I; i++) acc += x[i] * (float)w[i]; y[o] = acc * scale[o]; } } /* quantizza un weight f32 [O,I] -> int8 q[O,I] + scala[O], simmetrica per riga. * Replica quant_dequant() del Python: scale = amax(|w|, riga)/qmax, q = round(w/scale). */ static void quantize_rows(const float *w, int8_t *q, float *scale, int O, int I, int bits) { int qmax = (1 << (bits - 1)) - 1; /* 8->127, 4->7, 2->1 */ #pragma omp parallel for schedule(static) for (int o = 0; o < O; o++) { const float *wr = w + (int64_t)o * I; float amax = 0.f; for (int i = 0; i < I; i++) { float a = fabsf(wr[i]); if (a > amax) amax = a; } float s = amax / qmax; if (s < 1e-8f) s = 1e-8f; scale[o] = s; int8_t *qr = q + (int64_t)o * I; for (int i = 0; i < I; i++) { int v = (int)lrintf(wr[i] / s); if (v > qmax) v = qmax; if (v < -qmax-1) v = -qmax-1; qr[i] = (int8_t)v; } } } /* rmsnorm su una riga di lunghezza D, in-place su out (out puo' essere == x) */ static void rmsnorm_row(float *out, const float *x, const float *w, int D, float eps) { double ms = 0; for (int i = 0; i < D; i++) ms += (double)x[i]*x[i]; float r = 1.f / sqrtf((float)(ms / D) + eps); for (int i = 0; i < D; i++) out[i] = x[i] * r * w[i]; } static void softmax_row(float *x, int n) { float m = -1e30f; for (int i = 0; i < n; i++) if (x[i] > m) m = x[i]; float s = 0; for (int i = 0; i < n; i++) { x[i] = expf(x[i]-m); s += x[i]; } for (int i = 0; i < n; i++) x[i] /= s; } /* ---------- caricamento ---------- */ static void load_cfg(Cfg *c, const char *snap) { char path[2048]; snprintf(path, sizeof(path), "%s/config.json", snap); FILE *f = fopen(path, "rb"); if(!f){perror(path);exit(1);} fseek(f,0,SEEK_END); long n=ftell(f); fseek(f,0,SEEK_SET); char *buf = malloc(n+1); if(fread(buf,1,n,f)!=(size_t)n){} buf[n]=0; fclose(f); char *arena=NULL; jval *r = json_parse(buf, &arena); c->hidden = (int)json_get(r,"hidden_size")->num; c->n_layers = (int)json_get(r,"num_hidden_layers")->num; c->n_heads = (int)json_get(r,"num_attention_heads")->num; c->n_kv_heads= (int)json_get(r,"num_key_value_heads")->num; c->n_experts = (int)json_get(r,"num_experts")->num; c->topk = (int)json_get(r,"num_experts_per_tok")->num; c->inter = (int)json_get(r,"intermediate_size")->num; c->vocab = (int)json_get(r,"vocab_size")->num; c->head_dim = c->hidden / c->n_heads; jval *th = json_get(r,"rope_theta"); c->theta = th ? (float)th->num : 10000.f; jval *ep = json_get(r,"rms_norm_eps"); c->eps = ep ? (float)ep->num : 1e-5f; jval *nt = json_get(r,"norm_topk_prob"); c->norm_topk = (nt && nt->t==J_BOOL) ? nt->boolean : 0; free(buf); free(arena); } static float *load_t(Model *m, const char *name) { int64_t n = st_numel(&m->S, name); if (n < 0) { fprintf(stderr, "missing %s\n", name); exit(1); } float *p = falloc(n); st_read_f32(&m->S, name, p, 0); /* densa: niente DONTNEED, resta residente */ return p; } static void model_init(Model *m, const char *snap, int cap, int bits) { memset(m, 0, sizeof(*m)); m->quant_bits = bits; load_cfg(&m->c, snap); st_init(&m->S, snap); Cfg *c = &m->c; double t0 = now_s(); m->embed = load_t(m, "model.embed_tokens.weight"); m->lm_head = load_t(m, "lm_head.weight"); m->final_norm = load_t(m, "model.norm.weight"); m->L = calloc(c->n_layers, sizeof(Layer)); char nm[256]; for (int i = 0; i < c->n_layers; i++) { Layer *l = &m->L[i]; #define LD(field, suffix) snprintf(nm,sizeof(nm),"model.layers.%d." suffix,i); l->field = load_t(m,nm) LD(in_ln, "input_layernorm.weight"); LD(post_ln,"post_attention_layernorm.weight"); LD(q, "self_attn.q_proj.weight"); LD(k, "self_attn.k_proj.weight"); LD(v, "self_attn.v_proj.weight"); LD(o, "self_attn.o_proj.weight"); LD(qn,"self_attn.q_norm.weight"); LD(kn,"self_attn.k_norm.weight"); LD(gate, "mlp.gate.weight"); #undef LD } m->cache = calloc(c->n_layers, sizeof(LCache)); for (int i = 0; i < c->n_layers; i++) { m->cache[i].cap = cap; m->cache[i].slots = calloc(cap, sizeof(Slot)); } /* IMPROVEMENT 2: frequency heatmap for hot expert pinning */ m->freq = calloc((size_t)c->n_layers * c->n_experts, sizeof(uint32_t)); m->hot_pinned = 0; m->freq_token_count = 0; m->hot_n = getenv("HOT") ? atoi(getenv("HOT")) : 0; m->warmup_tokens = getenv("WARMUP") ? atoi(getenv("WARMUP")) : 5; m->token_count = 0; /* PREDICTION A: routing momentum — EMA of gate logits across tokens. * Initialized to zero; first token sets EMA = fresh logits. */ m->momentum_logits = calloc((size_t)c->n_layers * c->n_experts, sizeof(float)); float sv = getenv("SMOOTH") ? (float)atof(getenv("SMOOTH")) : 0.3f; if (sv < 0.f) sv = 0.f; if (sv > 0.95f) sv = 0.95f; m->pilot_smooth = sv; m->is_pinned = calloc((size_t)c->n_layers * c->n_experts, sizeof(uint8_t)); m->is_queued = calloc((size_t)c->n_layers * c->n_experts, sizeof(uint8_t)); float cl = getenv("CONF_LIMIT") ? (float)atof(getenv("CONF_LIMIT")) : 0.92f; if (cl < 0.1f) cl = 0.1f; if (cl > 1.0f) cl = 1.0f; m->pilot_conf_limit = cl; m->dense_load_s = now_s() - t0; // Persistent Hot Pinning: try to load hot_pinned.bin char pinpath[512]; snprintf(pinpath, sizeof(pinpath), "%s/hot_pinned.bin", snap); FILE *pinf = fopen(pinpath, "rb"); if (pinf) { size_t expected_size = (size_t)c->n_layers * c->n_experts; if (fread(m->is_pinned, 1, expected_size, pinf) == expected_size) { m->hot_pinned = 1; printf("[HOT] Loaded persistent pinning from %s\n", pinpath); if (g_pilot) { ensure_pilot_worker_started(m); for (int l = 0; l < c->n_layers; l++) { for (int e = 0; e < c->n_experts; e++) { if (m->is_pinned[l * c->n_experts + e]) { unsigned w = __atomic_load_n(&pilot_w, __ATOMIC_RELAXED); unsigned r = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); if (w - r < 4096) { pilot_q[w & 4095].l = l; pilot_q[w & 4095].e = e; pthread_mutex_lock(&g_pilot_mx); m->is_queued[l * c->n_experts + e] = 1; pthread_mutex_unlock(&g_pilot_mx); __atomic_store_n(&pilot_w, w + 1, __ATOMIC_RELEASE); } } } } printf("[HOT] Pre-loading pinned experts into cache...\n"); double t_wait = now_s(); while (1) { unsigned r = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); unsigned w = __atomic_load_n(&pilot_w, __ATOMIC_ACQUIRE); if (r == w) break; sleep_ms(2); } printf("[HOT] Pre-loaded in %.1fs!\n", now_s() - t_wait); } } fclose(pinf); } } static void slot_ensure_allocated(Model *m, Slot *s) { if (s->g) return; Cfg *c = &m->c; int64_t ng = (int64_t)c->inter * c->hidden; int64_t nd = (int64_t)c->hidden * c->inter; int8_t *w_block = malloc(ng + ng + nd); if (!w_block) { fprintf(stderr, "Error: Out of memory allocating slot weights block\n"); exit(1); } s->g = w_block; s->u = w_block + ng; s->d = w_block + ng + ng; float *s_block = falloc(c->inter + c->inter + c->hidden); s->gs = s_block; s->us = s_block + c->inter; s->ds = s_block + c->inter + c->inter; s->pinned = 0; } static void load_expert_merged(Model *m, int layer, int eid, Slot *s) { char nm[256], qsnm[256]; snprintf(nm, sizeof(nm), "model.layers.%d.mlp.experts.%d.merged_weight", layer, eid); snprintf(qsnm, sizeof(qsnm), "model.layers.%d.mlp.experts.%d.qs", layer, eid); st_read_raw(&m->S, nm, s->g, 1); st_read_raw(&m->S, qsnm, s->gs, 1); } /* ---------- cache expert: ritorna i pesi quantizzati (q+scale) da cache o disco ---------- */ static void expert_get(Model *m, int layer, int eid, Slot **out) { LCache *lc = &m->cache[layer]; pthread_mutex_lock(&g_pilot_mx); for (int i = 0; i < lc->n; i++) if (lc->slots[i].eid == eid) { m->hits++; lc->slots[i].used = ++m->clock; *out = &lc->slots[i]; pthread_mutex_unlock(&g_pilot_mx); return; } m->miss++; Cfg *c = &m->c; Slot *s; if (lc->n < lc->cap) { s = &lc->slots[lc->n++]; slot_ensure_allocated(m, s); } else { /* LRU eviction — skip pinned and in-flight (eid==-1) slots */ int lru = -1; for (int i = 0; i < lc->n; i++) { if (lc->slots[i].pinned || lc->slots[i].eid < 0) continue; if (lru < 0 || lc->slots[i].used < lc->slots[lru].used) lru = i; } if (lru < 0) lru = 0; /* all pinned/in-flight: fallback evict oldest */ s = &lc->slots[lru]; s->pinned = 0; } s->eid = -1; s->used = ++m->clock; pthread_mutex_unlock(&g_pilot_mx); load_expert_merged(m, layer, eid, s); pthread_mutex_lock(&g_pilot_mx); s->eid = eid; s->pinned = m->is_pinned[layer * c->n_experts + eid]; s->used = ++m->clock; *out = s; pthread_mutex_unlock(&g_pilot_mx); } /* ---------- IMPROVEMENT 2: pin top-N hot experts per layer ---------- */ static void pin_hot_experts(Model *m) { Cfg *c = &m->c; if (m->hot_n <= 0 || m->hot_pinned) return; m->hot_pinned = 1; int is_dynamic = (m->hot_n >= 100); double thresh = is_dynamic ? (double)m->hot_n / 1000.0 : 0.0; int pinned_total = 0; for (int l = 0; l < c->n_layers; l++) { uint32_t *freq_l = m->freq + (int64_t)l * c->n_experts; uint64_t layer_total = 0; for (int e = 0; e < c->n_experts; e++) layer_total += freq_l[e]; if (layer_total == 0) continue; int max_pin = m->cache[l].cap - 8; if (max_pin < 4) max_pin = 4; int hn = is_dynamic ? max_pin : (m->hot_n < c->n_experts ? m->hot_n : c->n_experts); if (hn > 256) hn = 256; int hot_eids[256]; int actual_hn = 0; for (int k = 0; k < hn; k++) { int best = -1; uint32_t bv = 0; for (int e = 0; e < c->n_experts; e++) { int already = 0; for (int j = 0; j < k; j++) if (hot_eids[j] == e) { already = 1; break; } if (!already && freq_l[e] > bv) { bv = freq_l[e]; best = e; } } if (best < 0 || bv == 0) break; if (is_dynamic && bv < thresh * layer_total) break; hot_eids[k] = best; actual_hn++; } for (int k = 0; k < actual_hn; k++) { int eid = hot_eids[k]; m->is_pinned[l * c->n_experts + eid] = 1; LCache *lc = &m->cache[l]; int found = 0; pthread_mutex_lock(&g_pilot_mx); for (int i = 0; i < lc->n; i++) { if (lc->slots[i].eid == eid) { lc->slots[i].pinned = 1; found = 1; break; } } pthread_mutex_unlock(&g_pilot_mx); if (!found) { unsigned w = __atomic_load_n(&pilot_w, __ATOMIC_RELAXED); unsigned r = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); if (w - r < 4096) { pilot_q[w & 4095].l = l; pilot_q[w & 4095].e = eid; __atomic_store_n(&pilot_w, w + 1, __ATOMIC_RELEASE); } } pinned_total++; } } if (is_dynamic) { printf("[HOT] Dynamic Pinned %d experts total (thresh=%.1f%%) after %d warmup tokens\n", pinned_total, thresh * 100.0, m->freq_token_count); } else { printf("[HOT] Pinned %d experts (top-%d/layer) after %d warmup tokens\n", pinned_total, m->hot_n, m->freq_token_count); } } /* ---------- RoPE su un vettore di una testa (head_dim) a posizione assoluta pos ---------- */ static void rope_head(float *x, int pos, const Cfg *c) { int h = c->head_dim / 2; for (int j = 0; j < h; j++) { float inv = powf(c->theta, -2.0f * j / c->head_dim); float ang = pos * inv, cs = cosf(ang), sn = sinf(ang); float a = x[j], b = x[j+h]; x[j] = a*cs - b*sn; x[j+h] = b*cs + a*sn; } } /* attenzione sui token nuovi x[S,hidden]; pos_base = posizione assoluta del primo token nuovo */ static void attention(Model *m, Layer *l, int layer, float *x, int S, int pos_base, float *out) { Cfg *c = &m->c; int H = c->n_heads, hd = c->head_dim, D = c->hidden; float *q = falloc((int64_t)S*D), *k = falloc((int64_t)S*D), *vv = falloc((int64_t)S*D); matmul(q, x, l->q, S, D, D); matmul(k, x, l->k, S, D, D); matmul(vv, x, l->v, S, D, D); /* qk-norm sull'intero vettore hidden, poi RoPE per testa */ for (int s = 0; s < S; s++) { rmsnorm_row(q + (int64_t)s*D, q + (int64_t)s*D, l->qn, D, c->eps); rmsnorm_row(k + (int64_t)s*D, k + (int64_t)s*D, l->kn, D, c->eps); int pos = pos_base + s; for (int hh = 0; hh < H; hh++) { rope_head(q + (int64_t)s*D + hh*hd, pos, c); rope_head(k + (int64_t)s*D + hh*hd, pos, c); } } /* scrive k,v nella kv-cache alle posizioni pos_base..pos_base+S-1 */ for (int s = 0; s < S; s++) for (int hh = 0; hh < H; hh++) { int t = pos_base + s; memcpy(m->K[layer] + ((int64_t)hh*m->max_t + t)*hd, k + (int64_t)s*D + hh*hd, hd*sizeof(float)); memcpy(m->V[layer] + ((int64_t)hh*m->max_t + t)*hd, vv + (int64_t)s*D + hh*hd, hd*sizeof(float)); } int Tk = pos_base + S; /* numero di key totali disponibili */ float scale = 1.f / sqrtf((float)hd); float *ctx = falloc((int64_t)S*D); #pragma omp parallel for collapse(2) schedule(static) for (int hh = 0; hh < H; hh++) { for (int s = 0; s < S; s++) { int qpos = pos_base + s; const float *qv = q + (int64_t)s*D + hh*hd; float sc[4096]; for (int t = 0; t <= qpos; t++) { /* causale: t <= qpos */ const float *kv = m->K[layer] + ((int64_t)hh*m->max_t + t)*hd; float acc = 0; for (int dd = 0; dd < hd; dd++) acc += qv[dd]*kv[dd]; sc[t] = acc * scale; } softmax_row(sc, qpos+1); float *cx = ctx + (int64_t)s*D + hh*hd; for (int dd = 0; dd < hd; dd++) cx[dd] = 0; for (int t = 0; t <= qpos; t++) { const float *vrow = m->V[layer] + ((int64_t)hh*m->max_t + t)*hd; float a = sc[t]; for (int dd = 0; dd < hd; dd++) cx[dd] += a * vrow[dd]; } } } (void)Tk; matmul(out, ctx, l->o, S, D, D); free(q); free(k); free(vv); free(ctx); } /* MoE sui token x[S,hidden] -> out[S,hidden] */ static void moe(Model *m, Layer *l, int layer, float *x, int S, float *out) { Cfg *c = &m->c; int D = c->hidden, E = c->n_experts, K = c->topk, I = c->inter; float *logits = falloc((int64_t)S*E); matmul(logits, x, l->gate, S, D, E); memset(out, 0, (int64_t)S*D*sizeof(float)); float *g = falloc(I), *u = falloc(I), *hh = falloc(D); for (int s = 0; s < S; s++) { float *pr = logits + (int64_t)s*E; if (m->momentum_logits && m->pilot_smooth > 0.f) { float *ema = m->momentum_logits + (int64_t)layer * E; int is_zero = 1; for (int e = 0; e < E; e++) { if (ema[e] != 0.f) { is_zero = 0; break; } } if (is_zero) { for (int e = 0; e < E; e++) ema[e] = pr[e]; } else { for (int e = 0; e < E; e++) { ema[e] = (1.f - m->pilot_smooth) * pr[e] + m->pilot_smooth * ema[e]; } } } softmax_row(pr, E); /* top-K indici (selezione parziale) */ int idx[64]; float val[64]; for (int kk = 0; kk < K; kk++) { int best = -1; float bv = -1e30f; for (int e = 0; e < E; e++) { int taken = 0; for (int j = 0; j < kk; j++) if (idx[j]==e){taken=1;break;} if (!taken && pr[e] > bv) { bv = pr[e]; best = e; } } idx[kk] = best; val[kk] = bv; } if (c->norm_topk) { float sm=0; for(int kk=0;kkhot_pinned && m->freq) { uint32_t *freq_l = m->freq + (int64_t)layer * E; for (int kk = 0; kk < K; kk++) if (idx[kk] >= 0) freq_l[idx[kk]]++; } const float *xs = x + (int64_t)s*D; for (int kk = 0; kk < K; kk++) { Slot *e; expert_get(m, layer, idx[kk], &e); matmul_q(g, xs, e->g, e->gs, D, I); /* gate_proj [I,D] */ matmul_q(u, xs, e->u, e->us, D, I); /* up_proj [I,D] */ for (int i = 0; i < I; i++) { float gv = g[i]; g[i] = (gv / (1.f + expf(-gv))) * u[i]; } matmul_q(hh, g, e->d, e->ds, I, D); /* down_proj [D,I] */ float w = val[kk]; float *os = out + (int64_t)s*D; for (int d = 0; d < D; d++) os[d] += w * hh[d]; } } free(logits); free(g); free(u); free(hh); } static float *step(Model *m, const int *ids, int S, int pos_base) { Cfg *c = &m->c; int D = c->hidden; if (g_pilot && m->token_count > 0) { unsigned r = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); __atomic_store_n(&pilot_w, r, __ATOMIC_RELEASE); pthread_mutex_lock(&g_pilot_mx); memset(m->is_queued, 0, (size_t)c->n_layers * c->n_experts); pthread_mutex_unlock(&g_pilot_mx); } float *x = falloc((int64_t)S*D); for (int s = 0; s < S; s++) memcpy(x + (int64_t)s*D, m->embed + (int64_t)ids[s]*D, D*sizeof(float)); float *nrm = falloc((int64_t)S*D), *tmp = falloc((int64_t)S*D); for (int i = 0; i < c->n_layers; i++) { Layer *l = &m->L[i]; for (int s = 0; s < S; s++) rmsnorm_row(nrm + (int64_t)s*D, x + (int64_t)s*D, l->in_ln, D, c->eps); attention(m, l, i, nrm, S, pos_base, tmp); for (int64_t j = 0; j < (int64_t)S*D; j++) x[j] += tmp[j]; /* IMPROVEMENT 1: PILOT=1 -> 1-layer lookahead */ if (g_pilot >= 1 && S <= 8 && i + 1 < c->n_layers) pilot_prefetch(m, i + 1, x, S); for (int s = 0; s < S; s++) rmsnorm_row(nrm + (int64_t)s*D, x + (int64_t)s*D, l->post_ln, D, c->eps); moe(m, l, i, nrm, S, tmp); for (int64_t j = 0; j < (int64_t)S*D; j++) x[j] += tmp[j]; /* PREDICTION IMPROVEMENT C (Residual gate trick): * PILOT=2 -> prefetch layer i+2 using completed state x (containing MoE residual). */ if (g_pilot >= 2 && S <= 8 && i + 2 < c->n_layers) pilot_prefetch(m, i + 2, x, S); if (g_pilot >= 3 && S <= 8 && i + 3 < c->n_layers) pilot_prefetch(m, i + 3, x, S); } /* IMPROVEMENT 2: count tokens; trigger hot pinning after warmup */ m->token_count++; m->freq_token_count++; if (!m->hot_pinned && m->hot_n > 0 && m->freq_token_count >= m->warmup_tokens) pin_hot_experts(m); m->kv_len = pos_base + S; float *last = falloc(D); rmsnorm_row(last, x + (int64_t)(S-1)*D, m->final_norm, D, c->eps); float *logit = falloc(c->vocab); matmul(logit, last, m->lm_head, 1, D, c->vocab); free(x); free(nrm); free(tmp); free(last); return logit; } static void pilot_realload(Model *m, int layer, int eid) { LCache *lc = &m->cache[layer]; Cfg *c = &m->c; pthread_mutex_lock(&g_pilot_mx); for (int i = 0; i < lc->n; i++) { if (lc->slots[i].eid == eid) { m->is_queued[layer * c->n_experts + eid] = 0; pthread_mutex_unlock(&g_pilot_mx); return; } } Slot *s; if (lc->n < lc->cap) { s = &lc->slots[lc->n++]; slot_ensure_allocated(m, s); } else { /* LRU eviction — skip pinned and in-flight (eid==-1) slots */ int lru = -1; for (int i = 0; i < lc->n; i++) { if (lc->slots[i].pinned || lc->slots[i].eid < 0) continue; if (lru < 0 || lc->slots[i].used < lc->slots[lru].used) lru = i; } if (lru < 0) { m->is_queued[layer * c->n_experts + eid] = 0; pthread_mutex_unlock(&g_pilot_mx); return; /* all pinned/in-flight, skip */ } s = &lc->slots[lru]; s->pinned = 0; } s->eid = -1; s->used = ++m->clock; pthread_mutex_unlock(&g_pilot_mx); load_expert_merged(m, layer, eid, s); pthread_mutex_lock(&g_pilot_mx); s->eid = eid; s->pinned = m->is_pinned[layer * c->n_experts + eid]; s->used = ++m->clock; m->is_queued[layer * c->n_experts + eid] = 0; pthread_mutex_unlock(&g_pilot_mx); } static void *pilot_worker(void *arg) { (void)arg; while (1) { unsigned r = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); unsigned w = __atomic_load_n(&pilot_w, __ATOMIC_ACQUIRE); if (r == w) { sleep_ms(1); continue; } int layer = pilot_q[r & 4095].l; int eid = pilot_q[r & 4095].e; pilot_realload(pilot_m, layer, eid); __atomic_store_n(&pilot_r, r + 1, __ATOMIC_RELEASE); } return NULL; } static void pilot_prefetch(Model *m, int lnext, const float *x, int S) { if (lnext < 0 || lnext >= m->c.n_layers) return; Cfg *c = &m->c; int D = c->hidden, E = c->n_experts; ensure_pilot_worker_started(m); float *logits = falloc((int64_t)S * E); Layer *l = &m->L[lnext]; // PREDICTION IMPROVEMENT B: Apply RMSNorm to x using destination layer's post_ln // This scales inputs to the distribution expected by l->gate. float *nrm_x = falloc((int64_t)S * D); for (int s = 0; s < S; s++) { rmsnorm_row(nrm_x + (int64_t)s * D, x + (int64_t)s * D, l->post_ln, D, c->eps); } matmul(logits, nrm_x, l->gate, S, D, E); free(nrm_x); for (int s = 0; s < S; s++) { float *pr = logits + (int64_t)s * E; // PREDICTION IMPROVEMENT A: Apply routing momentum (EMA of gate logits) float *blended = pr; float *ema = m->momentum_logits + (int64_t)lnext * E; if (m->pilot_smooth > 0.f) { blended = falloc(E); int is_zero = 1; for (int e = 0; e < E; e++) { if (ema[e] != 0.f) { is_zero = 0; break; } } if (is_zero) { for (int e = 0; e < E; e++) { ema[e] = pr[e]; blended[e] = pr[e]; } } else { for (int e = 0; e < E; e++) { blended[e] = (1.f - m->pilot_smooth) * pr[e] + m->pilot_smooth * ema[e]; ema[e] = blended[e]; // update EMA } } } int cand = 0; int idx[128]; float max_logit = -1e30f; for (int e = 0; e < E; e++) { if (blended[e] > max_logit) max_logit = blended[e]; } float *exps = falloc(E); float sum_exps = 0.f; for (int e = 0; e < E; e++) { exps[e] = expf(blended[e] - max_logit); sum_exps += exps[e]; } float cum_sum = 0.f; int min_cand = c->topk; int max_cand = c->topk * g_wide; if (max_cand < min_cand) max_cand = min_cand; if (max_cand > 128) max_cand = 128; /* idx[] buffer bound */ if (max_cand > E) max_cand = E; for (int kk = 0; kk < max_cand; kk++) { int best = -1; float bv = -1.f; for (int e = 0; e < E; e++) { int taken = 0; for (int j = 0; j < kk; j++) if (idx[j] == e) { taken=1; break; } if (!taken && exps[e] > bv) { bv = exps[e]; best = e; } } if (best < 0) break; idx[kk] = best; cum_sum += bv; cand++; if (cum_sum >= m->pilot_conf_limit * sum_exps && cand >= min_cand) { break; } } free(exps); if (blended != pr) free(blended); /* IMPROVEMENT 5: sort candidates by eid for sequential SSD read locality */ for (int a = 0; a < cand-1; a++) for (int b = a+1; b < cand; b++) if (idx[b] >= 0 && (idx[a] < 0 || idx[a] > idx[b])) { int t = idx[a]; idx[a] = idx[b]; idx[b] = t; } for (int kk = 0; kk < cand; kk++) { int eid = idx[kk]; if (eid < 0) continue; int found = 0; pthread_mutex_lock(&g_pilot_mx); LCache *lc = &m->cache[lnext]; for (int z = 0; z < lc->n; z++) { if (lc->slots[z].eid == eid) { found = 1; break; } } pthread_mutex_unlock(&g_pilot_mx); if (!found) { int gidx = lnext * E + eid; pthread_mutex_lock(&g_pilot_mx); int already_queued = m->is_queued[gidx]; if (!already_queued) { m->is_queued[gidx] = 1; } pthread_mutex_unlock(&g_pilot_mx); if (!already_queued) { unsigned w2 = __atomic_load_n(&pilot_w, __ATOMIC_RELAXED); unsigned r2 = __atomic_load_n(&pilot_r, __ATOMIC_ACQUIRE); if (w2 - r2 < 4096) { pilot_q[w2 & 4095].l = lnext; pilot_q[w2 & 4095].e = eid; __atomic_store_n(&pilot_w, w2 + 1, __ATOMIC_RELEASE); } else { pthread_mutex_lock(&g_pilot_mx); m->is_queued[gidx] = 0; pthread_mutex_unlock(&g_pilot_mx); } } } } } free(logits); } /* generazione greedy. prompt[np] -> riempie out[np+n_new] */ static void generate(Model *m, const int *prompt, int np, int n_new, int *out) { Cfg *c = &m->c; m->max_t = np + n_new; m->K = calloc(c->n_layers, sizeof(float*)); m->V = calloc(c->n_layers, sizeof(float*)); for (int i = 0; i < c->n_layers; i++) { m->K[i] = falloc((int64_t)c->n_heads * m->max_t * c->head_dim); m->V[i] = falloc((int64_t)c->n_heads * m->max_t * c->head_dim); } for (int i = 0; i < np; i++) out[i] = prompt[i]; float *logit = step(m, prompt, np, 0); /* PREFILL */ int len = np; for (int s = 0; s < n_new; s++) { int best = 0; float bv = logit[0]; for (int i = 1; i < c->vocab; i++) if (logit[i] > bv) { bv = logit[i]; best = i; } free(logit); out[len++] = best; if (s == n_new - 1) break; int one = best; logit = step(m, &one, 1, len - 1); /* DECODE */ } } /* ---------- lettura ref.json ---------- */ static int *read_int_array(jval *o, const char *key, int *n_out) { jval *a = json_get(o, key); int *r = malloc(a->len * sizeof(int)); for (int i = 0; i < a->len; i++) r[i] = (int)a->kids[i]->num; *n_out = a->len; return r; } int main(int argc, char **argv) { const char *snap = getenv("SNAP"); if (!snap) { fprintf(stderr, "set SNAP=\n"); return 1; } g_pilot = getenv("PILOT") ? atoi(getenv("PILOT")) : 0; g_wide = getenv("WIDE") ? atoi(getenv("WIDE")) : 1; if (g_wide < 1) g_wide = 1; if (g_wide > 4) g_wide = 4; int hot_n = getenv("HOT") ? atoi(getenv("HOT")) : 0; int cap = argc > 1 ? atoi(argv[1]) : 16; int bits = argc > 2 ? atoi(argv[2]) : 8; if (bits < 2 || bits > 8) { fprintf(stderr, "quant_bits must be 2..8 (got %d)\n", bits); return 1; } const char *refpath = argc > 3 ? argv[3] : "ref.json"; float smooth = getenv("SMOOTH") ? (float)atof(getenv("SMOOTH")) : 0.3f; float conf = getenv("CONF_LIMIT") ? (float)atof(getenv("CONF_LIMIT")) : 0.92f; printf("== Streaming C engine v2.2 | cache=%d/layer bits=%d pilot=%d wide=%d hot=%d smooth=%.2f conf=%.2f ==\n", cap, bits, g_pilot, g_wide, hot_n, smooth, conf); FILE *f = fopen(refpath, "rb"); if (!f) { perror(refpath); return 1; } fseek(f,0,SEEK_END); long n=ftell(f); fseek(f,0,SEEK_SET); char *buf=malloc(n+1); if (fread(buf,1,n,f)!=(size_t)n) {} buf[n]=0; fclose(f); char *arena=NULL; jval *ref = json_parse(buf, &arena); int np, nfull; int *prompt = read_int_array(ref,"prompt_ids",&np); int *full = read_int_array(ref,"full_ids",&nfull); int n_new = nfull - np; Model m; model_init(&m, snap, cap, bits); printf("resident weights loaded in %.1fs | RSS after load: %.2f GB\n", m.dense_load_s, rss_gb()); int *out = malloc((np + n_new) * sizeof(int)); double t = now_s(); generate(&m, prompt, np, n_new, out); double dt = now_s() - t; int match = 0; printf("\nReference: "); for (int i=np;i