diff --git a/scripts/kld-gate-swift15.sh b/scripts/kld-gate-swift15.sh index 51742a0..b71e496 100755 --- a/scripts/kld-gate-swift15.sh +++ b/scripts/kld-gate-swift15.sh @@ -32,14 +32,14 @@ podman run --rm --name "$C" \ -v "$KLD_REF_DIR:/data/kld-ref:ro" \ "stilldeadcode/radiance@$PIN" \ --model /models/rad/qwen4exp-swift15-w4dn8-i8-hc8m.rad \ - --host-pool-mib 40960 --deterministic --gpu-headroom-mib 768 \ + --host-pool-mib 40960 --deterministic --gpu-headroom-mib 512 \ --num-speculative-tokens 0 \ --kv-cache-dtype fp8 --max-model-len 16384 \ --ngram-placement ram \ --override-chat-template /models/tpl.jinja \ --kld-ref /data/kld-ref --kld-out /data/kld-gate.json \ - --vram-kv-mib 3072 \ - --max-num-seqs 4 --max-num-batched-tokens 32768 \ + --vram-kv-mib 2048 \ + --max-num-seqs 4 --max-num-batched-tokens 16384 \ 2>&1 | tee "$LOG" rc=${PIPESTATUS[0]} [ "$rc" -eq 0 ] || { echo "KLD GATE BOOT FAILED rc=$rc; log: $LOG"; exit "$rc"; }