Frank
db69fc8192
Compiles the 5-subagent research fan-out (llama.cpp RPC, vLLM PP, bandwidth math, mixed-vendor experiments, Qwen3.6-27B spec methods) into the KB under docs/Pipeline Parallelism/ with an index, expected performance estimates (1/2.5/10 GbE), and an EDUCATIONAL-ONLY two-node Qwen3.6-27B Q8 split script set (MTP/DFlash/ngram-mod variants, DSpark noted as vLLM-only). Nothing here is deployed or intended to run.
3.2 KiB
3.2 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 ngram-mod
frank-default-small]
C[Qwen3.6-35B-A3B uncensored Q6_K_P
MoE 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 MTP sidecar
frank-default-large]
F[Qwen3.6-27B uncensored Q8_K_P
MTP-ONLY 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; chose MTP sidecar (2026-08-14) over DFlash (parallel premature-EOS bug)
- 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
Pipeline Parallelism
- Pipeline Parallelism — index of multi-node inference research and sample scripts
- Pipeline Parallelism/llama.cpp RPC — ggml-rpc-server +
--rpcdistributed inference - Pipeline Parallelism/vLLM Pipeline Parallelism — vLLM PP across machines
- Pipeline Parallelism/Ethernet Bandwidth Math — bytes per token and link feasibility
- Pipeline Parallelism/Mixed-Vendor Experiments — NVIDIA + Strix Halo real-world runs
- Pipeline Parallelism/Expected Performance — estimated tok/s over 1/2.5/10 GbE
- Pipeline Parallelism/Sample Script Set — educational two-node Qwen3.6-27B Q8 split
- Pipeline Parallelism/llama.cpp RPC — ggml-rpc-server +