Frank
3c2db64a78
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.
2.5 KiB
2.5 KiB
vLLM Scripts — Knowledge Base
Documentation for running vLLM inference on two local machines.
Deployment Topology
graph LR
subgraph Dankserver[NVIDIA Dankserver - Ubuntu 24.04]
A[RTX 3090 24GB + 62GB RAM]
B[llama.cpp DFlash
frank-default-small]
C[Qwen3.6-35B-A3B uncensored Q6_K_P
experts on CPU, port 7770]
A --> B --> C
end
subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
D[gfx1151 APU 30GiB phys / 96GiB GPU-visible]
E[llama.cpp DFlash draft
frank-default-large]
F[Qwen3.6-27B uncensored Q8_K_P
DFlash draft, port 7770]
D --> E --> F
end
G[LLM Clients / API] -->|HTTP :7770| B
G -->|HTTP :7770| E
Servers
| Server | GPU | VRAM / Memory | OS |
|---|---|---|---|
| Dankserver System Specs | NVIDIA RTX 3090 | 24 GB VRAM, 62 GB RAM | Ubuntu 24.04 |
| Dankclaw System Specs | AMD Radeon 8060S (Strix Halo) | 30 GiB physical / 96 GiB GPU-visible | Ubuntu 26.04 |
vLLM Reference
- VLLM Overview — installation, CLI, API, architecture, quantization, parallelism
- VLLM Index — quick reference with commands, endpoints, and parameter table
- deployment — deploy and update process for both servers
Memory Management
- RAM CPU Offloading in VLLM — KV cache swap between GPU VRAM and system RAM
- Hybrid CPU GPU Processing Dankserver — NVIDIA GPU compute with system RAM offload
- Shared Memory Architecture Dankclaw — AMD unified memory and ROCm configuration
Model Deployment
- Running Qwen3.6 35B A3B FP8 on Dankserver — MoE model (35B total, 3B active) on RTX 3090
- Running Qwen3.6 27B FP8 on Dankclaw — Dense model (27B) on Strix Halo APU
- frank-default-large-benchmark — backend/spec benchmark that drove the Dankclaw llama.cpp deployment
- frank-default-small-benchmark — ncmoe and batch/ubatch sweep that drove the Dankserver state
- Dankclaw Improvements — researched enhancements: self-hosted agentic tools, runtime tuning, server/OS settings
Speculative Decoding & Quantization
- DFlash DSpark Speculative Decoding — block diffusion (DFlash) and semi-autoregressive (DSpark) drafting on vLLM and llama.cpp
- Quantization by Hardware Architecture — which quant format fits which GPU/CPU