- PARALLEL=4 (800000 total ctx), batch=8192, ubatch=2048
- n-cpu-moe=32 (moved 8 expert layers back to GPU)
- ctx-checkpoints=4 for headroom during larger batch compute
- All other tunables unchanged (ngram-mod, no-mmap, no-kv-offload, q8_0/f16 KV)
Lower each stream to 200000 ctx (pool 600000) to free KV VRAM for the larger
batch. Add --no-mmap so the CPU-resident MoE experts load eagerly into RAM
(avoids decode page faults). Keep KV on GPU. Experts already fully on CPU.
Bigger logical/physical batches for prefill throughput. Enable
--ctx-checkpoints to park attention checkpoints in RAM, holding peak GPU
memory down so the larger ubatch fits the 24GB VRAM alongside 3x262144 KV
without OOM. Weight split unchanged (experts CPU, non-experts GPU).
Retire vllm-awq-qwen36 (AWQ) from target maps, README, deployment, KB index,
Dankserver specs, DFlash and FP8 docs. New dankserver runtime: upstream
llama.cpp, port 7770, alias frank-default-small, 3x262144 ctx, DFlash Q8_0
draft, MoE experts offloaded to CPU, attention+KV on GPU (K q8_0, V f16).
deploy.sh now maps dankserver to frank-default-small and symlinks its unit.
models.json: dankserver baseUrl -> :7770, contextWindow -> 262144.
llama.cpp splits --ctx-size across --parallel slots, so 262144 total gave
87552 per stream. Non-negotiable is 262144 per stream: total pool must be
786432.
llama.cpp service replacing retired vllm-awq-qwen36 on port 7770 with alias
frank-default-small. Wrapper sources frank-default-small.env for tunables:
3 parallel slots at 262144 ctx, draft-dflash n-max 7, KV K=q8_0 V=f16 on GPU,
all MoE experts on CPU (--n-cpu-moe 40), non-expert tensors on GPU, mmproj
vision + jinja. Unit: frank-default-small.service (ExecStart in dankserver
repo clone /home/dank/vLLM/scripts).
Update target maps (AGENTS, README, deployment, deploy.sh) from the retired
ROCmFPX llama.cpp stack to the active vLLM-ROCm CIRU INT4 service on port 7770
with MTP speculative decoding. Align Dankserver to the running
vllm-awq-qwen36 (AWQ, port 34401). Refresh KB pages: Dankclaw system specs
(gpu-mem-util 0.95, CIRU venv), quantization choices (INT4 primary, MXFP4
experiment), DFlash/DSpark Dankclaw section, and the KB index topology.
The launcher does not change directory, so process cwd becomes sys.path[0]
for the 'python -m ...registry' model-inspection subprocess. From the CIRU
package root, the top-level vllm/ repo dir shadows the editable install as a
namespace package, breaking lazy imports (SamplingParams) and failing model
architecture inspection. cd to /home/dank/ling3-ciru before exec.
- Normalize 'VLLM' to 'vLLM' in prose across 6 docs (32 occurrences; wikilink
targets untouched)
- Remove duplicated Environment Variables block in 27B Dankclaw doc
- Update stale model refs Qwen3-30B-A3B -> Qwen3.6-35B-A3B in example commands
- Fix VLLM Index: -- separators to em-dashes; correct model names on links
- README: document active services (ROCmFPX llama-server on Dankclaw, vLLM
AWQ on Dankserver), replace broken [[docs/README.md]] link with docs/index.md
- scripts/deploy.sh: target-aware deploy (dankclaw/dankserver). Pushes main,
pulls on the target, installs/enables systemd unit, restarts service, and
checks the health endpoint; --dry-run preview; pre-flight dirty-tree check
- docs/deployment.md: full deployment/update process with mermaid workflow,
target map, manual update commands, service units, and troubleshooting
- AGENTS.md: add Deployment & Update Process section (deploy.sh usage, target
map, mermaid workflow) and a Summary table row
- docs/index.md: crosslink deployment doc
- Podman container with CUDA GPU access
- DFlash speculative decoding via --spec-method dflash
- FP8 KV cache, 4 parallel streams, 262K context
- CPU expert offloading via --cpu-offload-gb
- systemd service for persistent runtime
- Replace --override-kv with --alias for model naming
- Validation script tests 1, 2, 3 parallel streams sequentially
- Model name confirmed: frank-default-large
- DFlash+ngram-mod: 17.11 tok/s vs DFlash alone: 18.34 tok/s
- ngram overhead not offset by acceptance rate at current settings
- Keeping in place for now, may tune ngram-mod params later
- Add second parallel prompt (Byzantine Empire history vs ML)
- Both hit 1024 tokens, combined 2048 in 111.6s = 18.34 tok/s
- Parallel throughput matches single-stream baseline
- Add --spec-type draft-dflash (was missing, DFlash was inactive)
- Change --load-mode from mlock to none (RLIMIT_MEMLOCK too small for 2.7GB)
- Increase validation max_tokens from 256 to 1024 with complex ML prompt
- Baseline: 18.76 tok/s (was 7.62 tok/s without DFlash)
Frank
Frank