#!/usr/bin/env bash # fork-validate.sh - validate a candidate build of the RX 580 llama.cpp fork against a reference build. # # Runs ON THE POD (Vulkan / RADV, RX 580). Prints PASS/FAIL/SKIP per check plus a summary; exits # nonzero if any check FAILs. Only touches its own scratch dir under /tmp, its own scratch ports and # processes it started itself (killed by explicit PID). Build dirs are only read. # # fork-validate.sh --build /root/arms/X/build --ref /root/llama.cpp/build [checks] [options] # # Checks (no check flag = --ops --concat --arbiter): # --ops test-backend-ops on Vulkan0 for CONCAT, FLASH_ATTN_EXT, MUL_MAT, MUL_MAT_ID, GET_ROWS # -> the fork's kernels and upstream's agree with the CPU reference; asserts the case count # is > 0 because "-b Vulkan" (no index) silently runs nothing and still prints OK. # --concat Vulkan concat tiled-transpose fast path (ggml_vk_concat, gate src_transposed_2d) # -> it fires at prefill and NOT at decode on a real hybrid (delta-net) model; it is the # fork's biggest prefill win, and taking it at decode once cost -17% decode. # Needs a build carrying the GGML_VK_CONCAT_FASTPATH knob (=0 off, =log report); # either --build has it or pass --concat-build DIR (candidate + the knob patch). # --arbiter on-demand VRAM sharing (LLAMA_SLEEP_VRAM_ONLY ...) with two real servers on a scratch # arena -> a cold server really gives its VRAM back (v-vram-release: the card-wide # delta over a baseline taken before the scratch servers start must drop by >= 70% of # what it added warm, and come back on restore; production's own DRM clients are # re-read each time and the check SKIPs if they moved by > 64 MiB), handoffs never # strand, release/restore is bit-exact, multimodal survives it, # and every shutdown path (mid-release, mid-wait, mid-generation, cold, warm, kill -9 of # a waiter) exits cleanly and hands the GPU token on. These are the past production # incidents (stranded requests, wedged token, exit 134 on cold teardown). # Then a-handoff-latency: ordinary handoff latency of --build vs --ref in the same # session (fresh server pairs, blocks ref,cand,cand,ref x 16 handoffs) -> FAIL if the # candidate median exceeds the reference median by more than max(25%, 200 ms). Two # production deploys were lost to arbiter changes that only showed up here. # --perf llama-bench, candidate vs reference, alternating ref,cand,cand,ref, on the 35B MoE # -> no prefill regression > 5% at depth 0/16k/32k (FAIL), decode tg256@d4096 # reported; peak VRAM per arm (FAIL if > 95% of the card). Compares MEDIANS of every # repetition sample pooled over a build's two arms (4 per prefill cell, 6 for decode), # never means: CPU contention on the node produces single catastrophic samples. # Needs llama-swap STOPPED (run it under /root/bench/moe/swapdown.sh); refuses to # run if any other llama process is up. Samples are kept in /perf.tsv. # --moecache MODEL # one arbiter server with --moe-cache-mib N on a MoE model, forced cold/warm twice # -> greedy output identical before/after (the expert-cache SLRU is re-initialised on # release; a stale SLRU maps experts to empty banks and produces garbage). # --moe-exact MODEL # the MoE routing-ids readback skip (F1, sched_copy_experts) is exact: MODEL (a MoE, # e.g. the --perf model) with every expert on the host, greedy, one prompt of >= 2x # the skip threshold ceil(4 * n_expert / n_expert_used) tokens (read from the GGUF; # 128 on the 35B) -> candidate output byte-identical to the reference, and, if the # candidate has the LLAMA_MOE_IDS_SKIP knob, to the candidate with the skip forced off # (=0); =log proves the skip engaged. Without the knob skip-engaged is SKIPped with the # batch-size argument. Needs the GPU to itself like --perf (same guard); about 3 model # loads, so run it in the same swapdown window as --perf. # # Options: # --concat-build DIR build with the GGML_VK_CONCAT_FASTPATH knob for --concat (default: --build) # --small MODEL small hybrid model for --concat/--arbiter (default: Qwen3.5-0.8B UD-Q4_K_XL) # --mmproj FILE its multimodal projector (default: mmproj-F16 next to it) # --perf-model MODEL model for --perf (default: Qwen3.6-35B-A3B UD-Q4_K_XL) # --moecache-args S extra server args for --moecache (default: "-ngl 99 --n-cpu-moe 30 -c 4096") # --moecache-mib N cache size for --moecache (default 2048; 256 never hits on a 26B and proves nothing) # --port-base N scratch ports N..N+2 (default 8091) # --keep keep the scratch dir even when everything passed (it is kept on any FAIL) # --moe-exact-args S server args for --moe-exact (default: "-ngl 99 --n-cpu-moe 99 -c 4096 -b 2048 # -ub 2048 -t 6"; keep the experts on the host and -ub >= the prompt) # --perf-report TSV only re-aggregate a saved /perf.tsv of an earlier --perf run and # apply the same gates (no GPU, no --build/--ref needed); runs nothing else # # Requirements: bash, coreutils, awk, sed, grep, curl, flock(1); gdb optional (makes the # SIGTERM-during-release case deterministic; it is not in the pod image and is lost on a pod restart, # then the case falls back to polling the log). No python/jq. # # Test only: FV_TEST_SHARED_GPU=1 skips the exclusive-GPU guard of --perf / --moe-exact, for running # the script against stub binaries. Never set it for a real measurement. set -u # ---------------------------------------------------------------- defaults HF=/root/.cache/huggingface/hub SMALL_DIR=$HF/models--unsloth--Qwen3.5-0.8B-GGUF/snapshots/6ab461498e2023f6e3c1baea90a8f0fe38ab64d0 SMALL=$SMALL_DIR/Qwen3.5-0.8B-UD-Q4_K_XL.gguf MMPROJ= PERF_MODEL=$HF/models--unsloth--Qwen3.6-35B-A3B-GGUF/snapshots/a483e9e6cbd595906af30beda3187c2663a1118c/Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf MOECACHE_MODEL= MOECACHE_ARGS="-ngl 99 --n-cpu-moe 30 -c 4096" MOECACHE_MIB=2048 MOEX_MODEL= MOEX_ARGS="-ngl 99 --n-cpu-moe 99 -c 4096 -b 2048 -ub 2048 -t 6" BUILD= ; REF= ; CONCAT_BUILD= PORT_BASE=8091 KEEP=0 DO_OPS=0 DO_CONCAT=0 DO_ARB=0 DO_PERF=0 DO_MOEC=0 DO_MOEX=0 PERF_REPORT= usage() { awk 'NR > 1 && /^#/ {sub(/^# ?/, ""); print; next} NR > 1 {exit}' "$0"; exit 2; } while [ $# -gt 0 ]; do case "$1" in --build) BUILD=$2; shift 2 ;; --ref) REF=$2; shift 2 ;; --ops) DO_OPS=1; shift ;; --concat) DO_CONCAT=1; shift ;; --arbiter) DO_ARB=1; shift ;; --perf) DO_PERF=1; shift ;; --moecache) DO_MOEC=1; MOECACHE_MODEL=$2; shift 2 ;; --moecache-args) MOECACHE_ARGS=$2; shift 2 ;; --moecache-mib) MOECACHE_MIB=$2; shift 2 ;; --moe-exact) DO_MOEX=1; MOEX_MODEL=$2; shift 2 ;; --moe-exact-args) MOEX_ARGS=$2; shift 2 ;; --concat-build) CONCAT_BUILD=$2; shift 2 ;; --small) SMALL=$2; shift 2 ;; --mmproj) MMPROJ=$2; shift 2 ;; --perf-model) PERF_MODEL=$2; shift 2 ;; --port-base) PORT_BASE=$2; shift 2 ;; --keep) KEEP=1; shift ;; --perf-report) PERF_REPORT=$(readlink -f "$2"); shift 2 ;; -h|--help) usage ;; *) echo "unknown argument: $1" >&2; usage ;; esac done [ -n "$PERF_REPORT" ] || { [ -n "$BUILD" ] && [ -n "$REF" ]; } || usage if [ $((DO_OPS + DO_CONCAT + DO_ARB + DO_PERF + DO_MOEC + DO_MOEX)) -eq 0 ]; then DO_OPS=1 DO_CONCAT=1 DO_ARB=1 fi [ -n "$MMPROJ" ] || MMPROJ=$(dirname "$SMALL")/mmproj-F16.gguf PA=$PORT_BASE PB=$((PORT_BASE + 1)) PC=$((PORT_BASE + 2)) # ---------------------------------------------------------------- reporting RESULTS=() NFAIL=0 ts() { date +%H:%M:%S; } log() { echo "[$(ts)] $*"; } pass() { RESULTS+=("PASS $1: $2"); echo "[$(ts)] PASS $1: $2"; } fail() { RESULTS+=("FAIL $1: $2"); echo "[$(ts)] FAIL $1: $2"; NFAIL=$((NFAIL + 1)); } skip() { RESULTS+=("SKIP $1: $2"); echo "[$(ts)] SKIP $1: $2"; } # check NAME CONDITION-RESULT(0/1) MESSAGE check() { if [ "$2" -eq 0 ]; then pass "$1" "$3"; else fail "$1" "$3"; fi; } now_ms() { date +%s%3N; } # ---------------------------------------------------------------- scratch + cleanup S=$(mktemp -d /tmp/fork-validate.XXXXXX) ARENA=$S/arena mkdir -p "$ARENA" cd "$S" || exit 2 # anything written to a relative path lands in the scratch dir PIDS=() # "pid:starttime" of every background process we start (starttime guards PID reuse) pid_alive() { # alive and not a zombie [ -r "/proc/$1/stat" ] || return 1 local st; st=$(sed 's/.*) //' "/proc/$1/stat" 2>/dev/null | awk '{print $1}') || return 1 [ -n "$st" ] && [ "$st" != Z ] } starttime() { sed 's/.*) //' "/proc/$1/stat" 2>/dev/null | awk '{print $20}'; } track() { PIDS+=("$1:$(starttime "$1")"); } ours() { # "pid:starttime" -> pid if that exact process is still alive local p=${1%%:*} t=${1#*:} pid_alive "$p" && [ "$(starttime "$p")" = "$t" ] && echo "$p" } cleanup() { local e p for e in "${PIDS[@]}"; do p=$(ours "$e") && kill -TERM "$p" 2>/dev/null; done local i=0 while [ $i -lt 50 ]; do local any=0 for e in "${PIDS[@]}"; do ours "$e" > /dev/null && any=1; done [ $any -eq 0 ] && break sleep 0.1; i=$((i + 1)) done for e in "${PIDS[@]}"; do p=$(ours "$e") && kill -KILL "$p" 2>/dev/null; done wait 2>/dev/null } finish() { local rc=$? trap - EXIT INT TERM HUP cleanup echo echo "==================== fork-validate summary ====================" echo "candidate: $BUILD ($(git -C "$BUILD/.." rev-parse --short HEAD 2>/dev/null || echo '?'))" echo "reference: $REF ($(git -C "$REF/.." rev-parse --short HEAD 2>/dev/null || echo '?'))" local r; for r in "${RESULTS[@]}"; do echo "$r"; done local np ns np=$(printf '%s\n' "${RESULTS[@]}" | grep -c '^PASS') ns=$(printf '%s\n' "${RESULTS[@]}" | grep -c '^SKIP') echo "total: $np PASS, $NFAIL FAIL, $ns SKIP" if [ $NFAIL -gt 0 ] || [ $KEEP -eq 1 ] || [ $rc -ne 0 ]; then echo "scratch kept: $S" else rm -rf "$S" fi [ $NFAIL -gt 0 ] && exit 1 exit $rc } trap finish EXIT trap 'echo "interrupted"; NFAIL=$((NFAIL + 1)); exit 130' INT TERM HUP # ---------------------------------------------------------------- environment sanity for v in $(env | sed -n 's/^\(GGML_[A-Za-z0-9_]*\|LLAMA_\(SLEEP\|VRAM\|MMPROJ\|ARG\|CACHE\|LOG\|MOE\)[A-Za-z0-9_]*\)=.*/\1/p'); do log "unsetting inherited $v"; unset "$v" done [ -n "$PERF_REPORT" ] || for d in "$BUILD" "$REF"; do [ -x "$d/bin/llama-server" ] || { echo "no llama-server in $d/bin" >&2; exit 2; } done case "$ARENA" in /dev/shm/llama-vram*) echo "refusing the production arena" >&2; exit 2 ;; esac VRAM_USED=$(ls /sys/class/drm/card*/device/mem_info_vram_used 2>/dev/null | head -1) VRAM_TOTAL=$(ls /sys/class/drm/card*/device/mem_info_vram_total 2>/dev/null | head -1) vram_mb() { echo $(( $(cat "$VRAM_USED") / 1048576 )); } port_busy() { # LISTEN socket on the port (v4 or v6) local hex; hex=$(printf '%04X' "$1") awk -v h=":$hex" '$4=="0A" && substr($2, length($2)-4)==h {f=1} END {exit !f}' /proc/net/tcp /proc/net/tcp6 2>/dev/null } [ -n "$PERF_REPORT" ] || for p in $PA $PB $PC; do port_busy "$p" && { echo "scratch port $p is in use" >&2; exit 2; } done log "scratch dir $S, ports $PA/$PB/$PC, VRAM used $(vram_mb) MiB" # ---------------------------------------------------------------- helpers: servers # start_server NAME BUILD PORT ENV-ASSIGNMENTS... -- SERVER-ARGS... (sets SPID, log at $S/NAME.log) start_server() { local name=$1 build=$2 port=$3; shift 3 local envs=() while [ $# -gt 0 ] && [ "$1" != -- ]; do envs+=("$1"); shift; done shift env LD_LIBRARY_PATH="$build/bin" "${envs[@]}" "$build/bin/llama-server" \ --host 127.0.0.1 --port "$port" "$@" >> "$S/$name.log" 2>&1 & SPID=$! track "$SPID" echo "=== start pid $SPID $(date +%T.%N)" >> "$S/$name.log.events" } # wait_health PORT PID TIMEOUT_S wait_health() { local t0; t0=$(now_ms) while [ $(( $(now_ms) - t0 )) -lt $(( $3 * 1000 )) ]; do pid_alive "$2" || return 1 [ "$(curl -s -m 2 -o /dev/null -w '%{http_code}' "http://127.0.0.1:$1/health")" = 200 ] && return 0 sleep 0.2 done return 1 } # wait_exit PID TIMEOUT_MS -> prints elapsed ms, returns 1 on timeout. Then reap with `wait PID`. wait_exit() { local t0; t0=$(now_ms) while pid_alive "$1"; do [ $(( $(now_ms) - t0 )) -ge "$2" ] && { echo $(( $(now_ms) - t0 )); return 1; } sleep 0.02 done echo $(( $(now_ms) - t0 )) } # stop_server PID -> SIGTERM, wait up to 20 s, sets RC and EXIT_MS stop_server() { kill -TERM "$1" 2>/dev/null EXIT_MS=$(wait_exit "$1" 20000) || { kill -KILL "$1" 2>/dev/null; } wait "$1" 2>/dev/null; RC=$? } # ---------------------------------------------------------------- helpers: locks (/proc/locks) lock_id() { # maj:min:inode as /proc/locks prints it (hex dev, decimal inode) local d; d=$(( 16#$(stat -c %D "$1") )) printf '%02x:%02x:%s' $(( (d >> 8) & 0xfff )) $(( (d & 0xff) | ((d >> 12) & 0xfff00) )) "$(stat -c %i "$1")" } lock_pids() { # FILE WRITE|READ -> PIDs holding a flock on it (granted, not blocked) [ -e "$1" ] || return 0 awk -v id="$(lock_id "$1")" -v m="$2" '$2=="FLOCK" && $4==m && $6==id {print $5}' /proc/locks } token_holder() { lock_pids "$ARENA/token.lock" WRITE | head -1; } holder_num() { local h; h=$(token_holder); echo "${h:-0}"; } # for arithmetic: 0 = nobody # wait_holder PID TIMEOUT_MS : until PID holds token.lock ("" = until nobody does) wait_holder() { local t0; t0=$(now_ms) while [ "$(token_holder)" != "$1" ]; do [ $(( $(now_ms) - t0 )) -ge "$2" ] && return 1 sleep 0.01 done echo $(( $(now_ms) - t0 )) } wait_want() { # PID TIMEOUT_MS : until PID holds want.lock shared (registered waiter) local t0; t0=$(now_ms) until lock_pids "$ARENA/want.lock" READ | grep -qx "$1"; do [ $(( $(now_ms) - t0 )) -ge "$2" ] && return 1 sleep 0.01 done } # ---------------------------------------------------------------- helpers: VRAM attribution # mem_info_vram_used is card-wide and includes production. Production's own share is read from the # DRM fdinfo of every process this script did not start (drm-memory-vram, deduplicated by # drm-client-id; summing fds double-counts shared buffers), so a production model that warms or # cools during a measurement is detected instead of being attributed to the scratch servers. drm_vram_kib() { # PID... -> KiB of VRAM held by the DRM clients of these processes local p fs=() for p in "$@"; do [ -d "/proc/$p/fdinfo" ] && fs+=("/proc/$p/fdinfo/"*); done [ ${#fs[@]} -gt 0 ] || { echo 0; return; } cat "${fs[@]}" 2>/dev/null | awk '/^pos:/ {c = ""} /^drm-client-id:/ {c = $2} /^drm-memory-vram:/ && c != "" {v = $2; if ($3 == "MiB") v *= 1024; m[c] = v} END {for (k in m) s += m[k]; print s + 0}' } prod_vram_mb() { # MiB of VRAM held by every process this script did not start local p e mine=" " others=() for e in "${PIDS[@]}"; do mine+="${e%%:*} "; done for p in /proc/[0-9]*; do p=${p#/proc/} case "$mine" in *" $p "*) ;; *) others+=("$p") ;; esac done echo $(( $(drm_vram_kib "${others[@]}") / 1024 )) } # ---------------------------------------------------------------- helpers: requests json_str() { sed -n 's/.*"'"$1"'":"\(\([^"\\]\|\\.\)*\)".*/\1/p' "$2" | head -1; } json_num() { grep -o "\"$1\":[0-9]*" "$2" | head -1 | cut -d: -f2; } # complete PORT OUTFILE JSON-BODY [TIMEOUT_S] -> prints HTTP code ("000" on timeout/refused) complete() { curl -sS -m "${4:-60}" -o "$2" -w '%{http_code}' -H 'Content-Type: application/json' \ -d "$3" "http://127.0.0.1:$1/completion" 2>>"$S/curl.err" || true } PROMPT='The history of the printing press began in' GREEDY="\"temperature\":0,\"top_k\":1,\"seed\":42" greedy_body() { # N_PREDICT CACHE_PROMPT [PROMPT] echo "{\"prompt\":\"${3:-$PROMPT}\",\"n_predict\":$1,$GREEDY,\"cache_prompt\":$2}" } LONG_BODY="{\"prompt\":\"Write a very long story about a lighthouse keeper.\",\"n_predict\":4000,\"ignore_eos\":true,$GREEDY,\"stream\":true}" # stream_bg PORT OUTFILE BODY -> starts a streaming request, sets CPID stream_bg() { curl -sS -N -m 300 -H 'Content-Type: application/json' -d "$3" \ "http://127.0.0.1:$1/completion" > "$2" 2>&1 & CPID=$!; track "$CPID" } wait_tokens() { # FILE N TIMEOUT_MS : until N SSE data lines arrived local t0; t0=$(now_ms) while [ "$(grep -c '^data: ' "$1" 2>/dev/null)" -lt "$2" ]; do [ $(( $(now_ms) - t0 )) -ge "$3" ] && return 1 sleep 0.05 done } scan_logs() { # NAME-PATTERN... -> prints offending lines grep -h -n -E 'GGML_ASSERT|Assertion|terminate called|Segmentation fault|core dumped|ErrorDeviceLost|ErrorOutOfDeviceMemory|DEVICE_LOST|vk::.*Error|GGML_ABORT|fatal error' "$@" 2>/dev/null | head -20 } # ================================================================ 1. ops run_ops() { local op out passed total for op in CONCAT FLASH_ATTN_EXT MUL_MAT MUL_MAT_ID GET_ROWS; do out=$S/ops-$op.log log "ops: test-backend-ops -b Vulkan0 -o $op" ( cd "$S" && LD_LIBRARY_PATH="$BUILD/bin" timeout 1800 "$BUILD/bin/test-backend-ops" -b Vulkan0 -o "$op" ) \ > "$out" 2>&1 local rc=$? # strip ANSI colours; "N/M tests passed" is printed once per tested backend read -r passed total < <(sed 's/\x1b\[[0-9;]*m//g' "$out" | sed -n 's/^ *\([0-9]*\)\/\([0-9]*\) tests passed.*/\1 \2/p' | head -1) passed=${passed:-0}; total=${total:-0} if [ $rc -eq 0 ] && [ "$total" -gt 0 ] && [ "$passed" -eq "$total" ] \ && sed 's/\x1b\[[0-9;]*m//g' "$out" | grep -q 'Backend Vulkan0: OK'; then pass "ops/$op" "$passed/$total cases on Vulkan0" else fail "ops/$op" "rc=$rc, $passed/$total passed (0 cases = wrong backend name); see $out" fi done } # ================================================================ 2. concat fast path # Method: llama-bench on the small hybrid model (qwen35: delta-net layers concat the conv state with # the transposed qkv in build_conv_state). (1) with the knob =log, count fast-path dispatches in a # prefill-only run (must be > 0, all with >= 32 tokens) and a decode-only run (must be 0, while the # perf logger proves CONCAT nodes did execute); (2) GGML_VK_PERF_LOGGER CONCAT time at prefill: the # unmodified candidate must match knob-on and be >= 2x faster than knob-off, which ties the # candidate binary itself (no knob) to the fast path. concat_us() { # LOG -> "count avg_us" over all perf-logger CONCAT lines awk '/^CONCAT: / {n += $2; t += $(NF-1)} END {if (n) printf "%d %.2f\n", n, t/n; else print "0 0"}' "$1" } run_concat() { local tb=$CONCAT_BUILD [ -n "$tb" ] || tb=$BUILD if ! grep -qa GGML_VK_CONCAT_FASTPATH "$tb/bin/libggml-vulkan.so" 2>/dev/null; then fail concat "no GGML_VK_CONCAT_FASTPATH knob in $tb (build the candidate + knob patch, pass --concat-build)" return fi [ -f "$SMALL" ] || { fail concat "small model missing: $SMALL"; return; } local common=(-m "$SMALL" -ngl 99 -fa 1 -lm none -t 6) local pp=(-p 512 -n 0 -b 512 -ub 512 -r 3) local tg=(-p 0 -n 32 -r 1) lb() { # BUILD OUT ENV... -- ARGS local b=$1 out=$2; shift 2 local envs=(); while [ "$1" != -- ]; do envs+=("$1"); shift; done; shift env LD_LIBRARY_PATH="$b/bin" GGML_VK_PERF_LOGGER=1 "${envs[@]}" "$b/bin/llama-bench" "${common[@]}" "$@" \ > "$out" 2>&1 } log "concat: llama-bench prefill/decode arms (perf logger on)" lb "$tb" "$S/cc-pp-log.log" GGML_VK_CONCAT_FASTPATH=log -- "${pp[@]}" lb "$tb" "$S/cc-tg-log.log" GGML_VK_CONCAT_FASTPATH=log -- "${tg[@]}" lb "$tb" "$S/cc-pp-off.log" GGML_VK_CONCAT_FASTPATH=0 -- "${pp[@]}" lb "$BUILD" "$S/cc-pp-cand.log" -- "${pp[@]}" lb "$tb" "$S/cc-pp-off2.log" GGML_VK_CONCAT_FASTPATH=0 -- "${pp[@]}" lb "$BUILD" "$S/cc-pp-cand2.log" -- "${pp[@]}" cat "$S/cc-pp-off2.log" >> "$S/cc-pp-off.log"; cat "$S/cc-pp-cand2.log" >> "$S/cc-pp-cand.log" local n_pp n_pp_small n_tg n_tg_concat n_pp=$(grep -c 'transpose fast path' "$S/cc-pp-log.log") n_pp_small=$(sed -n 's/.*transpose fast path, transposed ne0=\([0-9]*\).*/\1/p' "$S/cc-pp-log.log" | awk '$1 < 32' | wc -l) n_tg=$(grep -c 'transpose fast path' "$S/cc-tg-log.log") read -r n_tg_concat _ < <(concat_us "$S/cc-tg-log.log") local ne0s; ne0s=$(sed -n 's/.*transposed ne0=\([0-9]*\).*/\1/p' "$S/cc-pp-log.log" | sort -n | uniq -c | awk '{printf "%sx%s ", $1, $2}') check concat/prefill-fires $(( n_pp > 0 && n_pp_small == 0 ? 0 : 1 )) \ "$n_pp fast-path dispatches in the prefill run (transposed ne0: ${ne0s:-none})" check concat/decode-skips $(( n_tg == 0 && n_tg_concat > 0 ? 0 : 1 )) \ "$n_tg fast-path dispatches over $n_tg_concat executed CONCAT nodes in the decode run" local c_on c_off c_cand on off cand read -r c_on on < <(concat_us "$S/cc-pp-log.log") read -r c_off off < <(concat_us "$S/cc-pp-off.log") read -r c_cand cand < <(concat_us "$S/cc-pp-cand.log") local ok ok=$(awk -v on="$on" -v off="$off" -v c="$cand" 'BEGIN {print (c > 0 && on > 0 && off/c >= 2 && c/on < 1.5 && on/c < 1.5) ? 0 : 1}') check concat/candidate-timing "$ok" \ "prefill CONCAT avg: candidate ${cand} us, knob-on ${on} us, knob-off ${off} us (off/cand $(awk -v a="$off" -v b="$cand" 'BEGIN {printf "%.1f", (b > 0) ? a / b : 0}')x)" local t_on t_off t_cand t_on=$(grep -E '\| +pp512 ' "$S/cc-pp-log.log" | awk -F'|' '{print $(NF-1)}' | awk '{print $1}' | head -1) t_off=$(grep -E '\| +pp512 ' "$S/cc-pp-off.log" | awk -F'|' '{print $(NF-1)}' | awk '{print $1}' | tr '\n' ' ') t_cand=$(grep -E '\| +pp512 ' "$S/cc-pp-cand.log" | awk -F'|' '{print $(NF-1)}' | awk '{print $1}' | tr '\n' ' ') log "concat: pp512 t/s (perf logger on, so absolute speed is not representative): on $t_on | off $t_off | candidate $t_cand" } # ================================================================ 3. arbiter ARB_ENV=(LLAMA_SLEEP_VRAM_ONLY=1 "LLAMA_VRAM_ARENA=$ARENA" LLAMA_SLEEP_EVICT_KV=1 LLAMA_MMPROJ_ONDEMAND=1) ARB_ARGS=(-m "$SMALL" -c 8192 -ngl 99 -fa 1 -lm none --parallel 1 --no-warmup --reasoning off) A_PID= ; B_PID= start_a() { start_server A "$BUILD" "$PA" "${ARB_ENV[@]}" -- "${ARB_ARGS[@]}" --mmproj "$MMPROJ"; A_PID=$SPID; } start_b() { start_server B "$BUILD" "$PB" "${ARB_ENV[@]}" -- "${ARB_ARGS[@]}" --no-mmproj; B_PID=$SPID; } sleeps() { grep -c 'server entering sleeping state' "$1"; } make_red_ppm() { # 128x128 solid red, binary PPM (stb_image reads it; no image tools needed) local f=$S/red.ppm i printf '\377\000\000' > "$S/px" for i in 1 2 3 4 5 6 7 8 9 10 11 12 13 14; do cat "$S/px" "$S/px" > "$S/px2"; mv "$S/px2" "$S/px"; done { printf 'P6\n128 128\n255\n'; cat "$S/px"; } > "$f" base64 -w0 "$f" } run_arbiter() { [ -f "$SMALL" ] && [ -f "$MMPROJ" ] || { fail arbiter "model/mmproj missing: $SMALL $MMPROJ"; return; } local free_mb=$(( ( $(cat "$VRAM_TOTAL") - $(cat "$VRAM_USED") ) / 1048576 )) if [ $free_mb -lt 1536 ]; then fail arbiter "only $free_mb MiB VRAM free (< 1536): run inside the swapdown window"; return fi # card-wide and production VRAM before any scratch server exists (see prod_vram_mb) local v0 p0; v0=$(vram_mb); p0=$(prod_vram_mb) log "arbiter: $free_mb MiB VRAM free (card $v0 MiB used, production DRM clients $p0 MiB); starting A (mmproj) on :$PA" start_a wait_health "$PA" "$A_PID" 180 || { fail arbiter/start "A did not become healthy, see $S/A.log"; return; } # no-handoff reference: A has held the token since its load and never released local code ref_a code=$(complete "$PA" "$S/ref-a.json" "$(greedy_body 48 false)") ref_a=$(json_str content "$S/ref-a.json") [ "$code" = 200 ] && [ -n "$ref_a" ] || { fail arbiter/start "reference request on A: HTTP $code"; return; } [ "$(token_holder)" = "$A_PID" ] || { fail arbiter/start "A serves but does not hold token.lock"; return; } # ---- (v) VRAM really drops when A goes cold, and comes back when it warms again # A is alone on the scratch arena; a fake waiter on want.lock makes it release. Its footprint is # the card-wide delta against the baseline taken before A started; production's DRM clients are # re-read at every point, and if they moved the check is SKIPped (it cannot attribute the delta). local v_warm p_warm v_cold p_cold v_back p_back f_warm f_cold w k=0 sleep 0.3 v_warm=$(vram_mb); p_warm=$(prod_vram_mb); f_warm=$(( $(drm_vram_kib "$A_PID") / 1024 )) local added=$(( v_warm - v0 )) need need=$(( added * 7 / 10 )) ( exec 9<"$ARENA/want.lock"; flock -s 9; exec sleep 120 ) & w=$!; track "$w" if ! wait_holder "" 10000 > /dev/null; then fail arbiter/v-vram-release "A did not drop the token for a waiter within 10 s (holder $(token_holder))" else # the release frees before it unlocks; give the driver a moment to return the pages while [ $(( v_warm - $(vram_mb) )) -lt $need ] && [ $k -lt 30 ]; do sleep 0.1; k=$((k + 1)); done fi v_cold=$(vram_mb); p_cold=$(prod_vram_mb); f_cold=$(( $(drm_vram_kib "$A_PID") / 1024 )) kill "$w" 2>/dev/null; wait "$w" 2>/dev/null code=$(complete "$PA" "$S/v-a.json" "$(greedy_body 48 false)") sleep 0.3 v_back=$(vram_mb); p_back=$(prod_vram_mb) local pmove; pmove=$(printf '%s\n' "$p_warm" "$p_cold" "$p_back" | awk -v b="$p0" '{d = $1 - b; if (d < 0) d = -d; if (d > m) m = d} END {print m + 0}') local vmsg="card-wide over baseline: warm +${added} MiB, cold +$((v_cold - v0)) MiB (dropped $((v_warm - v_cold)), need >= ${need} = 70%), restored +$((v_back - v0)) MiB; A's own DRM clients warm ${f_warm} / cold ${f_cold} MiB; production ${p0} -> ${p_warm}/${p_cold}/${p_back} MiB" if [ "$pmove" -gt 64 ]; then skip arbiter/v-vram-release "production VRAM moved by ${pmove} MiB during the measurement, cannot attribute: $vmsg" elif [ "$added" -lt 64 ]; then fail arbiter/v-vram-release "A added only ${added} MiB when warm (measurement broken?): $vmsg" else check arbiter/v-vram-release $(( v_warm - v_cold >= need ? 0 : 1 )) "$vmsg" check arbiter/v-vram-restore $(( code == 200 && v_back - v0 >= need && $(holder_num) == A_PID ? 0 : 1 )) \ "HTTP $code, A holds the token: $([ "$(token_holder)" = "$A_PID" ] && echo yes || echo NO), restored +$((v_back - v0)) MiB (need >= ${need}), output $([ "$(json_str content "$S/v-a.json")" = "$ref_a" ] && echo identical || echo DIFFERENT)" [ "$(json_str content "$S/v-a.json")" = "$ref_a" ] || fail arbiter/v-vram-output "output after the release/restore differs from the reference" fi log "arbiter: starting B (text-only) on :$PB" start_b wait_health "$PB" "$B_PID" 180 || { fail arbiter/start "B did not become healthy, see $S/B.log"; return; } pass arbiter/start "A=$A_PID B=$B_PID up, reference output ${#ref_a} chars" # ---- (a)+(b) alternating handoffs local i port pid name bad=0 stranded=0 diff_a=0 diff_b=0 ref_b= lat=() holder_bad=0 for i in $(seq 0 30); do if [ $((i % 2)) -eq 0 ]; then port=$PB pid=$B_PID name=B; else port=$PA pid=$A_PID name=A; fi local t0 t1 out=$S/h$i.json t0=$(now_ms) code=$(complete "$port" "$out" "$(greedy_body 48 false)" 60) t1=$(now_ms) [ $i -gt 0 ] && lat+=($((t1 - t0))) if [ "$code" = 000 ]; then stranded=$((stranded + 1)); continue; fi [ "$code" != 200 ] && { bad=$((bad + 1)); continue; } local c; c=$(json_str content "$out") if [ $name = A ]; then [ "$c" = "$ref_a" ] || diff_a=$((diff_a + 1)) else if [ -z "$ref_b" ]; then ref_b=$c; elif [ "$c" != "$ref_b" ]; then diff_b=$((diff_b + 1)); fi; fi [ "$(token_holder)" = "$pid" ] || holder_bad=$((holder_bad + 1)) done local med max med=$(printf '%s\n' "${lat[@]}" | sort -n | awk '{a[NR]=$1} END {print a[int((NR+1)/2)]}') max=$(printf '%s\n' "${lat[@]}" | sort -n | tail -1) check arbiter/a-handoffs $(( stranded == 0 && bad == 0 && holder_bad == 0 ? 0 : 1 )) \ "30 handoffs: $stranded stranded, $bad non-200, $holder_bad served-without-token; request latency median ${med} ms, max ${max} ms" check arbiter/b-greedy-identical $(( diff_a == 0 && diff_b == 0 ? 0 : 1 )) \ "A: 15/15 == no-handoff reference ($diff_a differ); B: $diff_b of 15 differ from its first; A==B: $([ "$ref_a" = "$ref_b" ] && echo yes || echo no)" # ---- (b') KV / prompt cache survives an evict + restore (LLAMA_SLEEP_EVICT_KV=1) local p1 p2 c1 c2 code=$(complete "$PA" "$S/kv1.json" "$(greedy_body 32 true 'Explain in detail how a refrigerator moves heat from inside to outside')") complete "$PB" "$S/kv-b.json" "$(greedy_body 8 false)" > /dev/null [ "$(token_holder)" = "$B_PID" ] || log "warning: B does not hold the token before the KV re-check" complete "$PA" "$S/kv2.json" "$(greedy_body 32 true 'Explain in detail how a refrigerator moves heat from inside to outside')" > /dev/null p1=$(json_num prompt_n "$S/kv1.json"); p2=$(json_num prompt_n "$S/kv2.json") c1=$(json_str content "$S/kv1.json"); c2=$(json_str content "$S/kv2.json") check arbiter/b-kv-survives $(( ${p2:-99} < ${p1:-0} && ${#c1} > 0 ? 0 : 1 )) \ "prompt_n $p1 -> $p2 after evict/restore (cache reused), output $([ "$c1" = "$c2" ] && echo identical || echo DIFFERENT)" [ "$c1" = "$c2" ] || fail arbiter/b-kv-output "cached-prompt output changed across evict/restore" # ---- (c) image after release/restore complete "$PB" "$S/c-b.json" "$(greedy_body 8 false)" > /dev/null # A goes cold local cold_ok=1; [ "$(token_holder)" = "$B_PID" ] && cold_ok=0 local img; img=$(make_red_ppm) printf '{"messages":[{"role":"user","content":[{"type":"image_url","image_url":{"url":"data:image/x-portable-pixmap;base64,%s"}},{"type":"text","text":"What is the main color of this image? Answer with one word."}]}],"max_tokens":16,%s}' \ "$img" "$GREEDY" > "$S/c-body.json" code=$(curl -sS -m 120 -o "$S/c-a.json" -w '%{http_code}' -H 'Content-Type: application/json' \ -d @"$S/c-body.json" "http://127.0.0.1:$PA/v1/chat/completions" 2>>"$S/curl.err") local ans; ans=$(json_str content "$S/c-a.json") check arbiter/c-image-after-restore $(( cold_ok == 0 && ${#code} > 0 && code == 200 ? 0 : 1 )) \ "A cold before: $([ $cold_ok -eq 0 ] && echo yes || echo NO), HTTP $code, answer: '$ans'" echo "$ans" | grep -qi red || fail arbiter/c-image-answer "expected 'red', got '$ans'" # text right after the image path (encoder out, weights back) code=$(complete "$PA" "$S/c-a2.json" "$(greedy_body 48 false)") [ "$code" = 200 ] && [ "$(json_str content "$S/c-a2.json")" = "$ref_a" ] \ || fail arbiter/c-text-after-image "HTTP $code, output differs from reference after the image request" # ---- (g) kill -9 a waiter that holds want.lock -> the holder stops yielding stream_bg "$PA" "$S/g-a.sse" "$LONG_BODY"; local gcl=$CPID if ! wait_tokens "$S/g-a.sse" 3 30000; then fail arbiter/g-kill9-waiter "A did not start streaming"; else local s_before; s_before=$(sleeps "$S/A.log") complete "$PB" "$S/g-b.json" "$(greedy_body 8 false)" 60 > /dev/null & local gbc=$!; track "$gbc" if ! wait_want "$B_PID" 10000; then fail arbiter/g-kill9-waiter "B never registered on want.lock (setup)" else kill -KILL "$B_PID"; wait "$B_PID" 2>/dev/null kill "$gcl" 2>/dev/null; wait "$gcl" 2>/dev/null # end A's generation (client abort) sleep 2 local wl; wl=$(lock_pids "$ARENA/want.lock" READ | wc -l) check arbiter/g-kill9-waiter $(( $(holder_num) == A_PID && $(sleeps "$S/A.log") == s_before && wl == 0 ? 0 : 1 )) \ "after kill -9 of waiting B: want.lock readers $wl, token holder $(token_holder) (A=$A_PID), A sleeps +$(( $(sleeps "$S/A.log") - s_before ))" fi wait "$gbc" 2>/dev/null fi log "arbiter: restarting B" start_b wait_health "$PB" "$B_PID" 180 || { fail arbiter/restart "B did not come back"; return; } # ---- (e) SIGTERM while A waits for the token -> exits fast, never restores stream_bg "$PB" "$S/e-b.sse" "$LONG_BODY"; local ecl=$CPID wait_tokens "$S/e-b.sse" 3 30000 || { fail arbiter/e-term-waiting "B did not start streaming"; } complete "$PA" "$S/e-a.json" "$(greedy_body 8 false)" 30 > /dev/null & local eac=$!; track "$eac" if wait_want "$A_PID" 10000; then sleep 0.3 local t0 ms took_token=0 t0=$(now_ms); kill -TERM "$A_PID" while pid_alive "$A_PID"; do [ "$(token_holder)" = "$A_PID" ] && took_token=1 [ $(( $(now_ms) - t0 )) -gt 10000 ] && break sleep 0.01 done ms=$(( $(now_ms) - t0 )); wait "$A_PID"; RC=$? check arbiter/e-term-waiting $(( RC == 0 && ms <= 1500 && took_token == 0 && $(holder_num) == B_PID ? 0 : 1 )) \ "exit $RC in ${ms} ms, A took the token: $([ $took_token = 1 ] && echo YES || echo no), holder now $(token_holder) (B=$B_PID), log: $(grep -c 'no longer waiting for the GPU token' "$S/A.log") abort line(s)" else fail arbiter/e-term-waiting "A never registered on want.lock (setup)" stop_server "$A_PID" fi kill "$ecl" 2>/dev/null; wait "$ecl" "$eac" 2>/dev/null log "arbiter: restarting A" start_a wait_health "$PA" "$A_PID" 180 || { fail arbiter/restart "A did not come back"; return; } # ---- (d) SIGTERM during A's VRAM release -> exit 0 within ~2 s, B gets the token # A is warm (fresh load, first release also captures the host shadow: the longest release) local how sig_ms if command -v gdb > /dev/null; then how=gdb gdb -p "$A_PID" -batch -nx -ex 'set pagination off' -ex 'handle all nostop noprint pass' \ -ex 'break llama_context_release_device' -ex 'continue' \ -ex "shell date +%s%3N > $S/d.sig" -ex 'delete' -ex 'signal SIGTERM' > "$S/d-gdb.log" 2>&1 & local gpid=$!; track "$gpid" local k=0; until grep -q '^Continuing' "$S/d-gdb.log" || [ $k -gt 300 ]; do sleep 0.1; k=$((k + 1)); done sleep 0.5 else how=log-poll fi local s0; s0=$(sleeps "$S/A.log") complete "$PB" "$S/d-b.json" "$(greedy_body 8 false)" 60 > "$S/d-b.code" & local dbc=$!; track "$dbc" if [ $how = log-poll ]; then local k=0; until [ "$(sleeps "$S/A.log")" -gt "$s0" ] || [ $k -gt 2000 ]; do sleep 0.005; k=$((k + 1)); done now_ms > "$S/d.sig"; kill -TERM "$A_PID" else local k=0; until [ -s "$S/d.sig" ] || [ $k -gt 600 ]; do sleep 0.05; k=$((k + 1)); done fi if [ ! -s "$S/d.sig" ]; then fail arbiter/d-term-in-release "release breakpoint never hit ($how), see $S/d-gdb.log" kill "$gpid" 2>/dev/null; stop_server "$A_PID" else while pid_alive "$A_PID" && [ $(( $(now_ms) - $(cat "$S/d.sig") )) -lt 20000 ]; do sleep 0.01; done sig_ms=$(( $(now_ms) - $(cat "$S/d.sig") )) wait "$A_PID"; RC=$? wait "$dbc" local dcode; dcode=$(cat "$S/d-b.code") sleep 0.2 check arbiter/d-term-in-release $(( RC == 0 && sig_ms <= 2500 && dcode == 200 && $(holder_num) == B_PID ? 0 : 1 )) \ "SIGTERM inside llama_context_release_device ($how): A exit $RC in ${sig_ms} ms, B HTTP $dcode, holder $(token_holder) (B=$B_PID)" fi log "arbiter: restarting A" start_a wait_health "$PA" "$A_PID" 180 || { fail arbiter/restart "A did not come back"; return; } # ---- (f) SIGTERM mid-generation (streaming) stream_bg "$PA" "$S/f-a.sse" "$LONG_BODY"; local fcl=$CPID if ! wait_tokens "$S/f-a.sse" 10 30000; then fail arbiter/f-term-streaming "A did not start streaming"; else local t0 free_ms=-1 cl_ms=-1 exit_ms=-1 t0=$(now_ms); kill -TERM "$A_PID" while [ $(( $(now_ms) - t0 )) -lt 10000 ]; do [ $free_ms -lt 0 ] && [ -z "$(token_holder)" ] && free_ms=$(( $(now_ms) - t0 )) [ $cl_ms -lt 0 ] && ! pid_alive "$fcl" && cl_ms=$(( $(now_ms) - t0 )) [ $exit_ms -lt 0 ] && ! pid_alive "$A_PID" && exit_ms=$(( $(now_ms) - t0 )) [ $free_ms -ge 0 ] && [ $cl_ms -ge 0 ] && [ $exit_ms -ge 0 ] && break sleep 0.01 done wait "$A_PID"; RC=$?; wait "$fcl" 2>/dev/null local errev; errev=$(grep -c '"error"' "$S/f-a.sse") check arbiter/f-term-streaming $(( RC == 0 && errev > 0 && cl_ms >= 0 && free_ms >= 0 && free_ms <= 2500 && exit_ms >= 0 ? 0 : 1 )) \ "A exit $RC in ${exit_ms} ms, token free in ${free_ms} ms, client closed in ${cl_ms} ms with $errev error event(s) after $(grep -c '^data: ' "$S/f-a.sse") data lines" fi log "arbiter: restarting A" start_a wait_health "$PA" "$A_PID" 180 || { fail arbiter/restart "A did not come back"; return; } # ---- (h) clean shutdown warm and cold [ "$(token_holder)" = "$A_PID" ] || log "warning: A is not warm before the warm-shutdown case" stop_server "$A_PID" check arbiter/h-shutdown-warm $(( RC == 0 ? 0 : 1 )) "warm A: exit $RC in ${EXIT_MS} ms" start_a wait_health "$PA" "$A_PID" 180 || { fail arbiter/restart "A did not come back"; return; } complete "$PB" "$S/h-b.json" "$(greedy_body 8 false)" > /dev/null # A goes cold local acold=no; [ "$(token_holder)" = "$B_PID" ] && acold=yes stop_server "$A_PID" check arbiter/h-shutdown-cold $([ $RC -eq 0 ] && [ $acold = yes ] && echo 0 || echo 1) \ "cold A (B holds token: $acold): exit $RC in ${EXIT_MS} ms" stop_server "$B_PID" check arbiter/h-shutdown-warm-b $(( RC == 0 ? 0 : 1 )) "warm B: exit $RC in ${EXIT_MS} ms" local bad_lines; bad_lines=$(scan_logs "$S/A.log" "$S/B.log") check arbiter/log-scan $([ -z "$bad_lines" ] && echo 0 || echo 1) \ "$([ -z "$bad_lines" ] && echo 'no asserts / Vulkan errors in A/B logs' || echo "$bad_lines" | head -3 | tr '\n' ' ')" run_handoff_ab } # handoff_block BUILD TAG N : a fresh pair of BUILD on the scratch arena (A with mmproj, B text-only, # the same config as case a), one warm-up request on A, then N+1 alternating requests starting with # B. Request 0 is not a handoff (B holds the token after its load); the latency of requests 1..N is # appended to $S/lat-TAG.txt. HB_BAD counts setup failures, non-200s and answers without the token. handoff_block() { local build=$1 tag=$2 n=$3 a b i port pid code t0 t1 HB_BAD=0 : > "$S/lat-$tag.txt" start_server "L$tag-A" "$build" "$PA" "${ARB_ENV[@]}" -- "${ARB_ARGS[@]}" --mmproj "$MMPROJ"; a=$SPID if ! wait_health "$PA" "$a" 180; then HB_BAD=1; stop_server "$a"; return 1; fi complete "$PA" "$S/L$tag-warm.json" "$(greedy_body 8 false)" > /dev/null start_server "L$tag-B" "$build" "$PB" "${ARB_ENV[@]}" -- "${ARB_ARGS[@]}" --no-mmproj; b=$SPID if ! wait_health "$PB" "$b" 180; then HB_BAD=1; stop_server "$b"; stop_server "$a"; return 1; fi for i in $(seq 0 "$n"); do if [ $((i % 2)) -eq 0 ]; then port=$PB pid=$b; else port=$PA pid=$a; fi t0=$(now_ms) code=$(complete "$port" "$S/L$tag-$i.json" "$(greedy_body 48 false)" 60) t1=$(now_ms) if [ "$code" != 200 ] || [ "$(token_holder)" != "$pid" ]; then HB_BAD=$((HB_BAD + 1)); continue; fi [ "$i" -gt 0 ] && echo $((t1 - t0)) >> "$S/lat-$tag.txt" done stop_server "$b"; stop_server "$a" } # ---- (a') ordinary handoff latency, candidate vs reference, in one session # Two production deploys were lost to arbiter changes that passed the pathological cases but made # every ordinary handoff slower. Blocks run ref, cand, cand, ref (a fixed order once gave the later # slot about 9%); each build's median is over all its handoffs. FAIL if the candidate median exceeds # the reference median by more than max(25%, 200 ms): small absolute numbers are noisy. run_handoff_ab() { local n=16 blk k=0 bad_r=0 bad_c=0 tag log "arbiter: handoff latency A/B, blocks ref,cand,cand,ref x $n handoffs" : > "$S/lat-ref.txt"; : > "$S/lat-cand.txt" for blk in ref cand cand ref; do k=$((k + 1)); tag=$k-$blk local b; [ $blk = ref ] && b=$REF || b=$BUILD handoff_block "$b" "$tag" "$n" if [ $blk = ref ]; then bad_r=$((bad_r + HB_BAD)); else bad_c=$((bad_c + HB_BAD)); fi cat "$S/lat-$tag.txt" >> "$S/lat-$blk.txt" log "arbiter: block $tag median $(median < "$S/lat-$tag.txt") ms over $(wc -l < "$S/lat-$tag.txt") handoffs, $HB_BAD bad" done local mr mc nr nc maxr maxc limit mr=$(median < "$S/lat-ref.txt"); mc=$(median < "$S/lat-cand.txt") nr=$(wc -l < "$S/lat-ref.txt"); nc=$(wc -l < "$S/lat-cand.txt") maxr=$(sort -n "$S/lat-ref.txt" | tail -1); maxc=$(sort -n "$S/lat-cand.txt" | tail -1) if [ -z "$mr" ] || [ -z "$mc" ] || [ $bad_r -gt 0 ] || [ $bad_c -gt 0 ]; then fail arbiter/a-handoff-latency "blocks incomplete: reference $nr handoffs ($bad_r bad), candidate $nc ($bad_c bad); see $S/L*-*.log" return fi limit=$(awk -v r="$mr" 'BEGIN {d = r * 0.25; if (d < 200) d = 200; printf "%.0f", r + d}') check arbiter/a-handoff-latency "$(awk -v c="$mc" -v l="$limit" 'BEGIN {print (c > l) ? 1 : 0}')" \ "median handoff latency candidate ${mc} ms (n $nc, max $maxc) vs reference ${mr} ms (n $nr, max $maxr); limit ${limit} ms = ref + max(25%, 200 ms)" local bad_lines; bad_lines=$(scan_logs "$S"/L*-A.log "$S"/L*-B.log) [ -z "$bad_lines" ] || fail arbiter/a-handoff-latency-logs "$(echo "$bad_lines" | head -3 | tr '\n' ' ')" } # ================================================================ 4. perf vram_sampler() { # OUTFILE : max of mem_info_vram_used every 0.25 s, written continuously local m=0 v while :; do v=$(cat "$VRAM_USED"); [ "$v" -gt "$m" ] && { m=$v; echo "$m" > "$1"; }; sleep 0.25; done } # median of the numbers on stdin (one per line); empty input -> empty output median() { sort -g | awk '{a[NR] = $1} END {if (NR) printf "%.2f", (NR % 2) ? a[(NR + 1) / 2] : (a[NR / 2] + a[NR / 2 + 1]) / 2}'; } bench_samples() { # JSONL (llama-bench -o jsonl) -> "testt/s", one row per repetition sample sed -n 's/.*"n_prompt": *\([0-9]*\),.*"n_gen": *\([0-9]*\),.*"n_depth": *\([0-9]*\),.*"samples_ts": *\[\([^]]*\)\].*/\1 \2 \3 \4/p' "$1" | awk '{t = ($1 > 0) ? "pp" $1 : "tg" $2; if ($3 > 0) t = t " @ d" $3 for (i = 4; i <= NF; i++) {v = $i; gsub(/,/, "", v); if (v != "") print t "\t" v}}' } run_perf() { gpu_exclusive perf || return [ -f "$PERF_MODEL" ] || { fail perf "model missing: $PERF_MODEL"; return; } [ -x "$REF/bin/llama-bench" ] && [ -x "$BUILD/bin/llama-bench" ] || { fail perf "llama-bench missing"; return; } local common=(-m "$PERF_MODEL" -t 6 -ngl 99 -ncmoe 40 -b 2048 -ub 2048 -fa 1 -lm none -o jsonl -oe md) local arm k=0 base; base=$(vram_mb) log "perf: idle VRAM $base MiB; arms ref,cand,cand,ref" for arm in ref cand cand ref; do k=$((k + 1)) local b; [ $arm = ref ] && b=$REF || b=$BUILD local tag=$k-$arm vram_sampler "$S/perf-$tag.vram" & local vs=$!; track "$vs" # stdout: one JSON line per test with every repetition sample; stderr: the markdown table + logs log "perf: arm $tag pp sweep" LD_LIBRARY_PATH="$b/bin" "$b/bin/llama-bench" "${common[@]}" -p 2048 -n 0 -d 0,16384,32768 -r 2 \ > "$S/perf-$tag-pp.jsonl" 2> "$S/perf-$tag-pp.log" log "perf: arm $tag tg" LD_LIBRARY_PATH="$b/bin" "$b/bin/llama-bench" "${common[@]}" -p 0 -n 256 -d 4096 -r 3 \ > "$S/perf-$tag-tg.jsonl" 2> "$S/perf-$tag-tg.log" kill "$vs" 2>/dev/null; wait "$vs" 2>/dev/null { bench_samples "$S/perf-$tag-pp.jsonl"; bench_samples "$S/perf-$tag-tg.jsonl"; } | sed "s/^/$arm\t/" >> "$S/perf.tsv" echo "$arm $(cat "$S/perf-$tag.vram" 2>/dev/null || echo 0)" >> "$S/perf-vram.txt" done perf_report "$S/perf.tsv" local total; total=$(cat "$VRAM_TOTAL") local vr vc vr=$(awk '$1=="ref" && $2>m {m=$2} END {print m+0}' "$S/perf-vram.txt") vc=$(awk '$1=="cand" && $2>m {m=$2} END {print m+0}' "$S/perf-vram.txt") check perf/peak-vram $(( vc * 100 <= total * 95 ? 0 : 1 )) \ "peak VRAM reference $((vr / 1048576)) MiB, candidate $((vc / 1048576)) MiB of $((total / 1048576)) MiB (limit 95%)" } # perf_report TSV : "armtestt/s" rows, one per llama-bench repetition sample (arm = ref|cand). # Gates on the MEDIAN of all samples of a build (pooled over its arms): a single catastrophic # sample (CPU contention from the other pods on the node) moves a mean, not a median. perf_report() { local tsv=$1 echo echo "perf: median t/s over every repetition sample of both arms (order ref,cand,cand,ref)" printf '%-18s %24s %24s %8s\n' test "reference med (min-max, n)" "candidate med (min-max, n)" delta local tests t r c d rs cs tests=$(awk -F'\t' '{print $2}' "$tsv" | awk '!s[$0]++') local IFS_=$IFS; IFS=$'\n' for t in $tests; do r=$(awk -F'\t' -v t="$t" '$1=="ref" && $2==t {print $3}' "$tsv" | median) c=$(awk -F'\t' -v t="$t" '$1=="cand" && $2==t {print $3}' "$tsv" | median) rs=$(awk -F'\t' -v t="$t" '$1=="ref" && $2==t {n++; if (n == 1 || $3 < lo) lo = $3; if (n == 1 || $3 > hi) hi = $3} END {if (n) printf "%.1f-%.1f, %d", lo, hi, n}' "$tsv") cs=$(awk -F'\t' -v t="$t" '$1=="cand" && $2==t {n++; if (n == 1 || $3 < lo) lo = $3; if (n == 1 || $3 > hi) hi = $3} END {if (n) printf "%.1f-%.1f, %d", lo, hi, n}' "$tsv") d=$(awk -v r="$r" -v c="$c" 'BEGIN {if (r > 0) printf "%+.1f%%", (c/r - 1)*100}') printf '%-18s %24s %24s %8s\n' "$t" "$r ($rs)" "$c ($cs)" "$d" case "$t" in pp*) if [ -z "$r" ] || [ -z "$c" ] || [ "$(awk -v r="$r" -v c="$c" 'BEGIN {print (c < 0.95*r)}')" = 1 ]; then fail "perf/$t" "candidate median $c vs reference median $r t/s ($d, limit -5%)" else pass "perf/$t" "candidate median $c vs reference median $r t/s ($d)" fi ;; tg*) RESULTS+=("INFO perf/$t: candidate median $c vs reference median $r t/s ($d; decode is CPU-bound and noisy here, not gated)") ;; esac done IFS=$IFS_ local n_tests; n_tests=$(echo "$tests" | grep -c '^pp') [ "$n_tests" -ge 3 ] || fail perf/rows "expected 3 pp rows, got $n_tests (see $S/perf-*-pp.log)" } # ================================================================ 5. MoE cache release/restore smoke run_moecache() { [ -f "$MOECACHE_MODEL" ] || { fail moecache "model missing: $MOECACHE_MODEL"; return; } local free_mb=$(( ( $(cat "$VRAM_TOTAL") - $(cat "$VRAM_USED") ) / 1048576 )) log "moecache: $free_mb MiB VRAM free; server on :$PC with --moe-cache-mib $MOECACHE_MIB" local arena=$S/arena-moec; mkdir -p "$arena" # -lv 4: the cache size and hit/miss stats are only logged at that verbosity # shellcheck disable=SC2086 start_server M "$BUILD" "$PC" LLAMA_SLEEP_VRAM_ONLY=1 "LLAMA_VRAM_ARENA=$arena" LLAMA_SLEEP_EVICT_KV=1 -- \ -m "$MOECACHE_MODEL" $MOECACHE_ARGS -fa 1 -lm none --parallel 1 --no-warmup --reasoning off -lv 4 \ --moe-cache-mib "$MOECACHE_MIB" local mp=$SPID wait_health "$PC" "$mp" 600 || { fail moecache "server did not start, see $S/M.log"; return; } # chat endpoint: an instruct model fed a raw prompt can loop, which says nothing about the cache local body="{\"messages\":[{\"role\":\"user\",\"content\":\"What are the three primary colors of light? Answer in one short sentence.\"}],\"max_tokens\":64,$GREEDY}" local outs=() i code w for i in 0 1 2; do code=$(curl -sS -m 300 -o "$S/m$i.json" -w '%{http_code}' -H 'Content-Type: application/json' \ -d "$body" "http://127.0.0.1:$PC/v1/chat/completions" 2>>"$S/curl.err") outs+=("$(json_str content "$S/m$i.json")") [ "$code" = 200 ] || { fail moecache "request $i: HTTP $code"; stop_server "$mp"; return; } [ $i -eq 2 ] && break # force a release: a fake waiter holds want.lock shared until the server drops the token ( exec 9<"$arena/want.lock"; flock -s 9; exec sleep 120 ) & w=$!; track "$w" local k=0; until [ -z "$(awk -v id="$(lock_id "$arena/token.lock")" '$2=="FLOCK" && $4=="WRITE" && $6==id' /proc/locks)" ] || [ $k -gt 600 ]; do sleep 0.05; k=$((k + 1)); done log "moecache: cycle $((i + 1)) cold, VRAM $(vram_mb) MiB" kill "$w"; wait "$w" 2>/dev/null done stop_server "$mp" local size hits rel res size=$(sed -n 's/.*MoE cache size = *\([0-9.]*\) MiB.*/\1/p' "$S/M.log" | head -1) hits=$(sed -n 's/.*llama_moe_cache: .* hits = \([0-9]*\),.*/\1/p' "$S/M.log" | awk '{s += $1} END {print s+0}') rel=$(grep -c 'released .* MiB of MoE cache' "$S/M.log"); res=$(grep -c 'restored .* MiB of MoE cache' "$S/M.log") check moecache/active $(( hits > 0 ? 0 : 1 )) \ "cache ${size:-?} MiB, $hits hits (0 hits = cache too small to ever reuse an expert, so a stale SLRU would go unnoticed), released ${rel}x restored ${res}x" local same=1; [ "${outs[0]}" = "${outs[1]}" ] && [ "${outs[1]}" = "${outs[2]}" ] && [ -n "${outs[0]}" ] && same=0 check moecache/identical $same "3 greedy answers across 2 cold/warm cycles $([ $same = 0 ] && echo identical || echo DIFFER): '$(echo "${outs[0]}" | cut -c1-80)'" local coh=1; echo "${outs[2]}" | grep -qi red && echo "${outs[2]}" | grep -qi green && echo "${outs[2]}" | grep -qi blue && coh=0 check moecache/coherent $coh "answer after the 2nd restore names red, green and blue" check moecache/shutdown $(( RC == 0 ? 0 : 1 )) "exit $RC" local bad_lines; bad_lines=$(scan_logs "$S/M.log") check moecache/log-scan $([ -z "$bad_lines" ] && echo 0 || echo 1) "${bad_lines:-clean}" } # ================================================================ 6. MoE routing-ids readback skip (F1) exactness # sched_copy_experts skips the ids readback when a split's ids tensor has n_tokens * n_expert_used >= # 4 * n_expert entries, i.e. for any ubatch of at least ceil(4 * n_expert / n_expert_used) tokens # (128 on a 256-expert / 8-used model). Method: the model with every MoE layer's experts on the host # (so the expert-copy callback runs), greedy, one prompt of >= 2x that many tokens in a single # ubatch: the prefill takes the skip and every decode step takes the readback. The candidate's # output must be byte-identical to the reference's and, when the build has the LLAMA_MOE_IDS_SKIP # knob, to the candidate with the skip forced off (=0), which proves the skip itself is exact even # when the reference build carries it too; =log then shows the skip engaged. gguf_u32() { # FILE KEY-SUFFIX -> uint32 value of the first GGUF metadata key ending in KEY-SUFFIX local off t off=$(head -c 67108864 "$1" | grep -abo -m1 -F "$2" | head -1 | cut -d: -f1) [ -n "$off" ] || return 1 off=$((off + ${#2})) # key string -> uint32 value type -> value t=$(od -An -tu4 -j "$off" -N4 "$1" | tr -d ' ') [ "$t" = 4 ] || [ "$t" = 5 ] || return 1 # GGUF_TYPE_UINT32 / INT32 od -An -tu4 -j $((off + 4)) -N4 "$1" | tr -d ' ' } gpu_exclusive() { # CHECK-NAME -> FAILs it and returns 1 unless nothing else can use the GPU [ "${FV_TEST_SHARED_GPU:-}" = 1 ] && { log "FV_TEST_SHARED_GPU=1: skipping the exclusive-GPU guard (script testing only)"; return 0; } if supervisorctl -c /root/supervisord.conf status llama-swap 2>/dev/null | grep -q RUNNING; then fail "$1" "llama-swap is RUNNING; run under /root/bench/moe/swapdown.sh"; return 1 fi local others; others=$(ps -eo pid=,comm= | awk '$2 ~ /^llama-(server|bench|cli)$/' | wc -l) [ "$others" -eq 0 ] || { fail "$1" "$others other llama processes are running"; return 1; } } moex_prompt() { # N_LINES -> a deterministic prose-like prompt (JSON-safe: no quotes or backslashes) local i for i in $(seq 1 "$1"); do printf 'Entry %d: the river town of Station%d ships %d barrels of grain and %d crates of salt each week to the harbour, and its council meets on day %d of the month. ' \ "$i" "$i" $(( (i * 37) % 101 + 3 )) $(( (i * 53) % 89 + 2 )) $(( (i * 7) % 28 + 1 )) done printf 'Question: which town ships the most barrels of grain each week? Answer:' } run_moe_exact() { gpu_exclusive moe-exact || return [ -f "$MOEX_MODEL" ] || { fail moe-exact "model missing: $MOEX_MODEL"; return; } local n_exp n_used n_exp=$(gguf_u32 "$MOEX_MODEL" .expert_count); n_used=$(gguf_u32 "$MOEX_MODEL" .expert_used_count) if [ -z "$n_exp" ] || [ -z "$n_used" ] || [ "$n_exp" -eq 0 ] || [ "$n_used" -eq 0 ]; then fail moe-exact "no expert_count / expert_used_count in $MOEX_MODEL (not a MoE model?)"; return fi local thr=$(( (4 * n_exp + n_used - 1) / n_used )) # tokens per ubatch where the skip starts local lines=$(( (2 * thr + 39) / 40 + 2 )) # ~45 tokens per line -> >= 2x the threshold local body body="{\"prompt\":\"$(moex_prompt "$lines")\",\"n_predict\":64,$GREEDY,\"cache_prompt\":false}" local knob=0; grep -qa LLAMA_MOE_IDS_SKIP "$BUILD/bin/libllama.so" 2>/dev/null && knob=1 log "moe-exact: n_expert $n_exp, n_expert_used $n_used -> skip at >= $thr tokens per ubatch; prompt of $lines lines; knob in candidate: $([ $knob = 1 ] && echo yes || echo no)" # arm NAME BUILD ENV... : one server, one request; sets MX_CONTENT / MX_PN, returns 1 on failure mx_arm() { local name=$1 b=$2; shift 2 # shellcheck disable=SC2086 start_server "$name" "$b" "$PC" "$@" -- -m "$MOEX_MODEL" $MOEX_ARGS -fa 1 -lm none --parallel 1 --no-warmup local p=$SPID code if ! wait_health "$PC" "$p" 900; then fail "moe-exact/$name" "server did not start, see $S/$name.log"; stop_server "$p"; return 1; fi code=$(complete "$PC" "$S/$name.json" "$body" 600) stop_server "$p" MX_CONTENT=$(json_str content "$S/$name.json"); MX_PN=$(json_num prompt_n "$S/$name.json") [ "$code" = 200 ] && [ -n "$MX_CONTENT" ] || { fail "moe-exact/$name" "HTTP $code, empty output; see $S/$name.log"; return 1; } [ "$RC" -eq 0 ] || log "warning: $name exited $RC" } local c_cand c_ref c_off pn if [ $knob = 1 ]; then mx_arm X-cand "$BUILD" LLAMA_MOE_IDS_SKIP=log || return else mx_arm X-cand "$BUILD" || return; fi c_cand=$MX_CONTENT; pn=${MX_PN:-0} if [ "$pn" -lt "$thr" ]; then fail moe-exact/prompt "prompt_n $pn < threshold $thr: the skip never ran, nothing was tested"; return fi mx_arm X-ref "$REF" || return c_ref=$MX_CONTENT check moe-exact/identical-ref $([ "$c_cand" = "$c_ref" ] && echo 0 || echo 1) \ "prompt_n $pn (>= $thr), 64 greedy tokens: candidate $([ "$c_cand" = "$c_ref" ] && echo == || echo '!=') reference ('$(echo "$c_cand" | cut -c1-60)')" if [ $knob = 1 ]; then mx_arm X-cand-noskip "$BUILD" LLAMA_MOE_IDS_SKIP=0 || return c_off=$MX_CONTENT check moe-exact/identical-noskip $([ "$c_cand" = "$c_off" ] && echo 0 || echo 1) \ "candidate with the skip (LLAMA_MOE_IDS_SKIP=log) $([ "$c_cand" = "$c_off" ] && echo == || echo '!=') candidate with the readback forced (=0)" local n_skip n_small n_skip=$(grep -c 'sched_copy_experts: ids readback skipped' "$S/X-cand.log") n_small=$(sed -n 's/.*ids readback skipped, n_ids=\([0-9]*\) n_expert=\([0-9]*\).*/\1 \2/p' "$S/X-cand.log" | awk '$1 < 4 * $2' | wc -l) check moe-exact/skip-engaged $(( n_skip > 0 && n_small == 0 ? 0 : 1 )) \ "$n_skip skips logged ($n_small below 4*n_expert), $(grep -c 'ids readback skipped' "$S/X-cand-noskip.log") with the skip forced off" else skip moe-exact/skip-engaged "candidate has no LLAMA_MOE_IDS_SKIP knob to observe it; by construction the prefill ubatch had $pn x $n_used = $((pn * n_used)) ids >= 4 x $n_exp, so the skip branch ran" fi local bad_lines; bad_lines=$(scan_logs "$S"/X-*.log) check moe-exact/log-scan $([ -z "$bad_lines" ] && echo 0 || echo 1) "${bad_lines:-clean}" } # ================================================================ main if [ -n "$PERF_REPORT" ]; then [ -r "$PERF_REPORT" ] || { echo "cannot read $PERF_REPORT" >&2; exit 2; } perf_report "$PERF_REPORT"; exit 0 fi [ $DO_OPS -eq 1 ] && run_ops [ $DO_CONCAT -eq 1 ] && run_concat [ $DO_ARB -eq 1 ] && run_arbiter [ $DO_PERF -eq 1 ] && run_perf [ $DO_MOEC -eq 1 ] && run_moecache [ $DO_MOEX -eq 1 ] && run_moe_exact exit 0