swift15: gate boots at the production pool (w4 gate_up experts are RAM-resident; disk tier refuses non-serving stored forms)

2026-10-08 03:14:20 -07:00
parent 3f8531179e
commit 058ea6cca8
1 changed files with 1 additions and 2 deletions
@@ -32,8 +32,7 @@ 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 \
-    --tp 2 --placement expert_tiered --weights-disk-tier \
-    --host-pool-mib 12288 --deterministic --gpu-headroom-mib 768 \
+    --host-pool-mib 40960 --deterministic --gpu-headroom-mib 768 \
    --num-speculative-tokens 0 \
    --kv-cache-dtype fp8 --max-model-len 16384 \
    --ngram-placement ram \