sync scripts from remotes: ROCmFPX llama-server.service (dankclaw), dankserver vLLM serve/validate; drop failed-attempt scripts

- llama-server.service: dankclaw migrated to ROCmFPX runtime (Ling-3.0-flash,
  draft-mtp, no-mmap/direct-io) from regular llama.cpp Qwen3.6-27B-DFlash
- serve-vllm-qwen36-dflash.sh: dankserver version (relies on image 'vllm serve'
  entrypoint; HF cache mounted read-write)
- validate-vllm.sh: dankserver multi-stream vLLM validation (4 unique prompts,
  1-4 streams, prompt+completion speed)
- remove superseded scripts: serve-llamacpp-dflash.sh, validate.sh,
  vllm-awq-qwen36-dflash-ampere.sh, vllm-qwen36.service

scripts/llama-server.service

@@ -1,12 +1,12 @@
 [Unit]
-Description=llama.cpp DFlash+MTP Inference Server (Qwen3.6-27B on ROCm)
+Description=llama.cpp Inference Runtime
 After=network.target
 
 [Service]
 Type=simple
 User=dank
 Group=dank
-ExecStart=/home/dank/llama.cpp/build/bin/llama-server --hf-repo unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 --spec-draft-hf Alittlehammmer/Qwen3.6-27B-DFlash-GGUF-llama.cpp:Q8_0 --spec-type draft-dflash --spec-draft-n-max 16 --device ROCm0 --spec-draft-device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 3 --ctx-size 600000 --batch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --alias frank-default-large --load-mode none
+ExecStart=/home/dank/GitPackages/ROCmFPX/build-strix-rocmfp4/bin/llama-server -hf raulvidis/Ling-3.0-flash-ROCmFP4-STRIX-MTP-GGUF:Q4_0 --spec-type draft-mtp --spec-draft-n-max 2 --device ROCm0 --gpu-layers all --fit on --fit-target 512 --parallel 2 --ctx-size 401400 --batch-size 8192 --ubatch-size 4096 --port 8080 --host 0.0.0.0 --threads 16 --alias frank-default-large --no-mmap --direct-io -lv 4 --timeout 7200 --chat-template-file /home/dank/LingFlash/chat_template.jinja
 Restart=on-failure
 RestartSec=10