fleet redo 2026-08-17: retire PP+NPU, new topology

- Move all previous scripts to old/scripts/ (retired PP/NPU-era) - frank-default-large: llama.cpp FastMTP on dankserver (HauhauCS Qwen3.8-27B IQ4_XS + FastMTP 32K draft + ngram-mod, K q8_0/V f16, 128K ctx, batch 2048/ubatch 1024, port 7770) - frank-default-small: vLLM ROCm on dankclaw (Avesed Qwen3.6-35B-A3B INT8 W8A8, full 262144 ctx, no KV quant, 4 seqs, batch 16384, ngram spec, port 52625) - retarget deploy.sh (dankserver/dankclaw, inline sudo, no helpers) - docs: deployment + index + AGENTS.md + README for new topology, superseded banners on retired docs, add frank-redo-2026-08-17 runbook
2026-08-17 15:23:46 -07:00
1 parent 136ee080c9
commit d9af7f1d19
@@ -0,0 +1,78 @@
+#!/usr/bin/env bash
+# bench-spec-matrix.sh - Qwen3.8-27B UD-Q8_K_XL speculative-decode matrix.
+# Matrix: spec_type {draft-mtp,ngram-mod | draft-mtp | ngram-mod}
+#         x --spec-draft-n-max {2..10} x --spec-draft-p-min {off, 0.8}
+# = 54 configs. Each: start llama-server, wait ready, 3 generations of a
+# 1100-token prompt (n_predict 200, default sampling), record timings.
+set -u
+
+MODEL=/home/dank/models/Qwen3.8-27B-UD-Q8_K_XL.gguf
+LLAMA_SERVER=/home/dank/llama.cpp/build/bin/llama-server
+PORT=7890
+DEVICE=ROCm0
+OUT=/tmp/spec_matrix_results.tsv
+RUNLOG=/tmp/spec_matrix_run.log
+PROMPT=$(python3 -c "print(\"The fleet of inference servers must remain available at all times. Operators monitor memory, throughput, and queue depth. \"*50)")
+N_OUT=200
+RUNS=3
+
+: > "$OUT"
+printf 'spec_type\tn_max\tp_min\trun\ttps\tpps\tdraft_acc\tdraft_n\tstop\n' >> "$OUT"
+
+cfg=0
+for spec in "draft-mtp,ngram-mod" "draft-mtp" "ngram-mod"; do
+  for n_max in 2 3 4 5 6 7 8 9 10; do
+    for p_min in none 0.8; do
+      cfg=$((cfg+1))
+      echo "=== CONFIG $cfg/54: spec=$spec n_max=$n_max p_min=$p_min $(date +%T) ===" | tee -a "$RUNLOG"
+      ARGS=(--model "$MODEL" --spec-type "$spec" --spec-draft-n-max "$n_max")
+      # Qwen3.8 bundles its MTP drafter inside the target GGUF; no separate
+      # --spec-draft-model file (llama.cpp auto-detects, b10411+).
+      if [[ "$p_min" != none ]]; then
+        ARGS+=(--spec-draft-p-min "$p_min")
+      fi
+      ARGS+=(--device "$DEVICE" --gpu-layers all --cache-type-k q8_0 --cache-type-v f16
+             --ctx-size 2048 --parallel 1 --batch-size 512 --ubatch-size 128
+             --temp 1.0 --top-k 20 --top-p 0.95 --min-p 0.0
+             --host 127.0.0.1 --port "$PORT")
+      "$LLAMA_SERVER" "${ARGS[@]}" > /tmp/matrix_server.log 2>&1 &
+      SPID=$!
+      ready=0
+      for i in $(seq 1 150); do
+        if curl -sf "http://127.0.0.1:$PORT/health" > /dev/null 2>&1; then ready=1; break; fi
+        if ! kill -0 "$SPID" 2>/dev/null; then break; fi
+        sleep 2
+      done
+      if [[ "$ready" != 1 ]]; then
+        echo "NOT_READY: spec=$spec n_max=$n_max p_min=$p_min" | tee -a "$RUNLOG"
+        tail -4 /tmp/matrix_server.log >> "$RUNLOG"
+        kill "$SPID" 2>/dev/null; wait "$SPID" 2>/dev/null
+        continue
+      fi
+      for r in 1 2 3; do
+        curl -s -m 300 -X POST "http://127.0.0.1:$PORT/completion" -H "Content-Type: application/json" \
+          -d "{\"prompt\": \"$PROMPT\", \"n_predict\": $N_OUT, \"stream\": false, \"cache_prompt\": false}" \
+          | python3 -c "
+import json,sys
+try:
+    d=json.load(sys.stdin)
+    t=d.get('timings',{})
+    row=[\"$spec\",\"$n_max\",\"$p_min\",\"$r\",
+         str(round(t.get('predicted_per_second',0),2)),
+         str(round(t.get('prompt_per_second',0),2)),
+         str(t.get('draft_n_accepted','')),
+         str(t.get('draft_n','')),
+         str(d.get('stop_type',''))]
+    with open(\"$OUT\",\"a\") as f:
+        f.write('\t'.join(row)+'\n')
+except Exception as e:
+    with open(\"$OUT\",\"a\") as f:
+        f.write('\t'.join([\"$spec\",\"$n_max\",\"$p_min\",\"$r\",\"ERR\",str(e),\"\",\"\",\"\"])+'\n')
+"
+      done
+      kill "$SPID" 2>/dev/null; wait "$SPID" 2>/dev/null
+      sleep 3
+    done
+  done
+done
+echo "=== MATRIX DONE $(date) ===" | tee -a "$RUNLOG"