dank/serverAppConfigs
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

frank-default-small: ncmoe 32 + ubatch 1024 from llama-bench sweep

Browse Source 
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.
This commit is contained in:
Frank
2026-08-13 22:56:24 -07:00
parent 0d09756430
commit 3c2db64a78
6 changed files with 145 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/deployment.md
+1 -1
View File
@@ -143,7 +143,7 @@ The active service on Dankclaw runs llama.cpp serving the HauhauCS Qwen3.6-27B u
### Dankserver — frank-default-small
The active service on Dankserver runs llama.cpp (upstream, `b10108+`) and serves the HauhauCS Qwen3.6-35B-A3B uncensored `Q6_K_P` model under the alias `frank-default-small` on port 7770. It uses **ngram-mod** speculative decoding (`--spec-ngram-mod-n-min 48 / n_max 64 / n_match 24`), **4 parallel slots** at 200000 context each (pool 800000), and mmproj vision. **35 of 40 MoE expert layers** stay on CPU (`--n-cpu-moe 35`); 5 expert layers' weights are back on GPU alongside all non-expert tensors (`--gpu-layers all`). KV stays on GPU (K=`q8_0`, V=`f16`). Batch 8192 / ubatch 2048, `--ctx-checkpoints 4`, `--no-mmap`. The unit file is `scripts/frank-default-small.service`, symlinked to `/etc/systemd/system/`. It launches through `scripts/serve-llama-frank-small.sh`, which reads tunables from `scripts/frank-default-small.env`.
The active service on Dankserver runs llama.cpp (upstream, `b10108+`) and serves the HauhauCS Qwen3.6-35B-A3B uncensored `Q6_K_P` model under the alias `frank-default-small` on port 7770. It uses **ngram-mod** speculative decoding (`--spec-ngram-mod-n-min 48 / n_max 64 / n_match 24`), **4 parallel slots** at 200000 context each (pool 800000), and mmproj vision. **32 of 40 MoE expert layers** stay on CPU (`--n-cpu-moe 32`); 8 expert layers' weights are back on GPU alongside all non-expert tensors (`--gpu-layers all`). KV stays on GPU (K=`q8_0`, V=`f16`). Batch 8192 / ubatch 1024, `--ctx-checkpoints 4`, `--no-mmap`. The unit file is `scripts/frank-default-small.service`, symlinked to `/etc/systemd/system/`. It launches through `scripts/serve-llama-frank-small.sh`, which reads tunables from `scripts/frank-default-small.env`.
> Note: this service replaced the retired `vllm-awq-qwen36` (AWQ 4-bit, port 34401) and the earlier `vllm-qwen36` (FP8) / `llama-server` (ROCmFPX) units. The repo tracks `main` on Dankserver at `/home/dank/vLLM`.