dank/serverAppConfigs
1
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity
174 Commits 60 Branches 8 Tags
8e4d63b68dce05ab7e16cecaa9cf3cffd150cf6a
Commit Graph
14 Commits
Author SHA1 Message Date
Frank 136ee080c9 docs: measured PP link math (H=5120 verified, 20.5 MB/ubatch wire), NIC inventory 
- Ethernet Bandwidth Math: new section 0 with live measurements
  (iperf 281-294 MB/s, ping RTT both paths, prefill 457.9 t/s at
  2.5GbE, per-ubatch wire 20.5 MB, 98k KV snapshot 3.45 GB blocking
  the slot 13.6 s, validated link-speed model: 386/458/505 t/s)
- System specs: NIC tables for both boxes; the 1 GbE USB-C adapter on
  the claw was silently routing the RPC path (unplugged 2026-08-17)
- PP Deployment: fix hidden-state size (10 KiB/direction, H=5120) and
  RTT-vs-bandwidth claim (decode RTT-bound; prefill+snapshot BW-bound)
 2026-08-17 05:06:41 -07:00
Frank 968066ff23 docs: boot policy (only PP units enabled), deploy.sh dankserver hazard, stale-claim cleanup 
- deployment.md: Boot Policy (2026-08-17) section (disabled units table,
  re-enable recipes, stale frank-restart-small.sh helper, broken
  deploy.sh dankserver target); Update Dankserver -> frank-pp-worker;
  condensed retired 35B history block and 2026-08-13 incident
- AGENTS.md: boot-policy note, target map fix (Q6_K, split 0.68),
  deploy.sh dankserver warning, obsolete quirk entries condensed
- README.md: rewrite active services/models tables (PP head + worker)
- index.md: topology fix (qwythos:9b, Q6_K split 0.68, NPU disabled)
- qwen3.8-spec-matrix.md: superseded configs merged into compact
  history; stale inline env block removed; bundled-head MTP note
- FastFlowLM, PP Deployment: boot-policy + enablement notes
- System Specs x2, DFlash doc, 35B FP8 doc, Ling docs: stale active
  claims fixed, retired banners, never-shipped plan stubbed
 2026-08-17 03:30:00 -07:00
Frank d72092b2c7 docs: record dual-f16 KV refit on frank-default-small (2026-08-14) 2026-08-14 12:59:10 -07:00
Frank 9d7643ec5d frank-default-small: ncmoe 35->36 for prefill stability 
Fix a live crash: cuBLAS cudaErrorInvalidValue in ggml_cuda_mul_mat_cublas
killed the service during a 145k-token prefill burst at ncmoe35/ub3072.

ncmoe 36 moves one more expert layer to CPU: frees ~0.75 GiB peak VRAM
(grid: peak 8606 vs 9360 MiB at ub3072) for -2% prefill / -2% decode.
Keeps prefill priority (top ubatch tier). Docs synced; noted fallback
GGML_CUDA_FORCE_MMQ=1 if pressure persists.
 2026-08-14 10:56:40 -07:00
Frank 01eb957f90 frank-default-small: prefill-max ncmoe 35 / ubatch 3072 
Prefill is the priority for this workload. Switch from decode-max
(ncmoe 32 / ubatch 1024) to prefill-max:
- n-cpu-moe 35, ubatch 3072: prefill ~1458 t/s (top tier), gen ~45.4 t/s,
  ~1.2 GiB headroom at the 800k pool.
- Gen is independent of ubatch; ub 3072 reaches best prefill with no
  decode cost. Docs synced (benchmark Chosen State, deployment, specs).
 2026-08-13 23:07:30 -07:00
Frank 3c2db64a78 frank-default-small: ncmoe 32 + ubatch 1024 from llama-bench sweep 
Swept ncmoe(30..40) x ubatch(256..4096) on the RTX 3090 (Qwen3.6-35B-A3B
Q6_K_P, pp16384/tg512, fit-target 0). Key findings:
- Generation depends only on ncmoe: 40.9 (ncmoe40) .. 51.1 (ncmoe30);
  ubatch/batch do not affect decode at all.
- Prefill + graph VRAM scale with ubatch; logical batch is irrelevant.
- VRAM model (peak + 11.44GiB KV pool + 2.2GiB overhead) reproduces the
  historical OOMs: ncmoe32-ub2048 sums ~24.4GiB > 24.

Chosen state: ncmoe 32 (8 expert layers on GPU), batch 8192, ubatch 1024.
  gen ~48.7 t/s (+7% vs prior ncmoe 35), prefill ~766 t/s, ~1.0GiB headroom.
Alternates: ncmoe34-ub2048 (gen 46.4, pp 1221, 1.5GiB) for prefill-heavy;
  ncmoe32-ub768 (1.3GiB) if headroom matters most.
Docs: new frank-default-small-benchmark.md; synced deployment.md + specs.
 2026-08-13 22:56:24 -07:00
Frank 209223cb4f Offload one more MoE expert to CPU on frank-default-small (34→35 of 40) 
- N_CPU_MOE 34→35: 5 expert layers on GPU instead of 6. Frees ~0.4-0.8 GiB
  VRAM for OOM safety after high-load sessions OOM'd at 32 and 33.
- Sync stale doc references (deployment.md, Dankserver System Specs.md)
  that still claimed 32/8; specs now estimate ~1.8 GiB headroom at 35.
 2026-08-13 20:18:20 -07:00
Frank 4c5a4a5f3b docs: frank-default-small — 4 parallel slots, batch 8192/2048, n-cpu-moe 32 
Update Dankserver System Specs and deployment to reflect the 4-stream config:
- 4 parallel slots (800000 total ctx), batch 8192 / ubatch 2048
- n-cpu-moe 32 (8 expert layers back on GPU)
- ~870 MiB VRAM headroom under 4-stream load
- Knob documented: n-cpu-moe 36 gives ~1.7 GiB more headroom if needed
 2026-08-11 03:13:36 -07:00
Frank 677b4af2a4 docs: frank-default-small now uses ngram-mod, DFlash retired 
- SWAT from DFlash (see ngram-mod benchmarks below); draft model
  not loaded. Active spec: --spec-type ngram-mod n_min=48/n_max=64/n_match=24.
- Update Dankserver specs, deployment.md, DFlash doc to ngram-mod.
- VRAM footprint: 14 GB (was 20 GB), ~10 GB free headroom.
 2026-08-11 02:41:33 -07:00
Frank 5c9e812221 docs: frank-default-small now 200000 ctx/stream, batch 3072/1536, --no-mmap 
Sync deployment.md, Dankserver specs, DFlash doc to the tuned config:
ctx reduced to 200000 per stream (pool 600000) to free KV VRAM for the larger
batch; --no-mmap eager RAM load; ctx-checkpoints 4; ~20GB VRAM / 32GB RAM.
models.json contextWindow -> 200000.
 2026-08-11 01:52:12 -07:00
Frank 35c44c4123 docs+deploy: Dankserver now llama.cpp frank-default-small (HauhauCS Q6_K_P + DFlash) 
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.
 2026-08-11 01:18:29 -07:00
Frank f650fff0aa docs: polish pass — fix stale names, duplicates, branding, and README 
- 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
 2026-08-10 21:12:23 -07:00
Frank 3a64c8f3dd docs: fact-check knowledge base against live machines and vLLM source 
Correct stale and incorrect facts after exhaustive verification:
- Dankclaw: NUMA node 0 = 31213 MB; disk 661G/1.1T/38%; vLLM 0.26.0 in
  /home/dank/vllm-rocm-venv (not vllm-env); clarify 96 GiB GPU-visible is a
  driver overcommit ceiling over 30 GiB physical (confirmed via sysfs
  mem_info_vram_total=103079215104)
- Dankserver: disk 729G/140G free/84%; /mnt/entropy 910G free; active service
  is vLLM EngineCore (22 GB), not llama-server; CPU model Ryzen 7 7700X
- index.md: Dankclaw 30GiB phys / 96GiB GPU-visible (was '61 GB unified');
  add deployment topology mermaid diagram
- vLLM defaults (from source): gpu_memory_utilization=0.92, max_num_seqs=128,
  swap_space removed (now --kv-offloading-size) across Overview/Index/RAM/Hybrid
- Quantization: FP8 not native on Ampere (RTX 3090) or RDNA 3.5 (gfx1151);
  add per-model hardware quantization notes; AWQ/GPTQ limited on ROCm
- Speculative decoding: add DFlash, DSpark, MTP, EAGLE3 to feature list
- Confirm Qwen3.6-27B and Qwen3.6-35B-A3B specs are correct (HF-verified)
- Production note: Dankclaw primary llama.cpp service runs ROCmFPX
  Ling-3.0-flash RocmFP4 MTP, not vLLM Qwen3.6-27B
 2026-08-10 20:59:33 -07:00
Frank 39db415348 feat: initialize vLLM scripts knowledge base 
- VLLM Overview: installation, CLI, API, architecture, quantization, parallelism
- VLLM Index: quick reference with commands, endpoints, parameters
- Dankserver System Specs: RTX 3090 24GB, 62GB RAM, Ubuntu 24.04
- Dankclaw System Specs: AMD Strix Halo APU, 61GB unified, ROCm 7.1
- RAM/CPU Offloading in VLLM: KV cache swap, gpu_memory_utilization, preemption
- Hybrid CPU/GPU Processing (Dankserver): NVIDIA GPU + system RAM configuration
- Shared Memory Architecture (Dankclaw): AMD unified memory and ROCm setup
- Running Qwen3.6 35B A3B FP8 on Dankserver: MoE model deployment guide
- Running Qwen3.6 27B FP8 on Dankclaw: dense model deployment guide
 2026-08-05 23:49:02 -07:00