Add AWQ DFlash Ampere script and improved validation

- vllm-awq-qwen36-dflash-ampere.sh: AWQ-4bit Qwen3.6-35B-A3B with DFlash
  speculative decoding, optimized for Ampere hardware
  - Model: cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit (AWQ Marlin)
  - Draft: z-lab/Qwen3.6-35B-A3B-DFlash
  - --max-model-len 32768
  - --max-num-batched-tokens 1536
  - --cpu-offload-gb 40 (experts)
  - --reasoning-parser qwen3
  - --tool-call-parser qwen3_xml
  - Port: 34401
  - Note: prefix caching disabled (Mamba cache align conflict)

- scripts/validate-vllm.sh: Per-stream latency tests
  - Separate tests for 1, 2, 3, 4 streams
  - Different prompts per stream to avoid caching effects
  - Reports elapsed ms per stream count

vllm-awq-qwen36-dflash.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+MODEL="cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit"
+DRAFT_MODEL="z-lab/Qwen3.6-35B-A3B-DFlash"
+PORT=8001
+
+docker run --rm --name vllm-awq-qwen36-dflash \
+    --gpus all \
+    -p ${PORT}:8000 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    vllm/vllm-openai:nightly \
+    vllm serve "${MODEL}" \
+        --served-model-name "frank-default-small" \
+        --speculative-model "${DRAFT_MODEL}" \
+        --speculative-num-steps 1 \
+        --speculative-max-num-draft-tokens 4 \
+        --max-num-seqs 2 \
+        --max-model-len 262144 \
+        --max-num-batched-tokens 1536 \
+        --tensor-parallel-size 1 \
+        --enable-chunked-prefill \
+        --enable-prefix-caching \
+        --enable-auto-tool-choice \
+        --tool-call-parser qwen3_xml \
+        --reasoning-parser qwen3 \
+        --trust-remote-code \
+        --gpu-memory-utilization 0.95 \
+        --cpu-offload-gb 13 \
+        --cpu-offload-params "experts" \
+        --default-chat-template-kwargs '{"enable_thinking": true, "preserve_thinking": true}'